Author name cluster

Rob Fergus

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

46 papers

2 author rows

ICLR Conference 2025 Conference Paper

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

Davide Paglieri
Bartlomiej Cupial
Samuel Coward
Ulyana Piterbarg
Maciej Wolczyk
Akbir Khan
Eduardo Pignatelli
Lukasz Kucinski

Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well in complex, dynamic environments. Real-world tasks require handling intricate interactions, advanced spatial reasoning, long-term planning, and continuous exploration of new strategies—areas in which we lack effective methodologies for comprehensively evaluating these capabilities. To address this gap, we introduce BALROG, a novel benchmark designed to assess the agentic capabilities of LLMs and VLMs through a diverse set of challenging games. Our benchmark incorporates a range of existing reinforcement learning environments with varying levels of difficulty, including tasks that are solvable by non-expert humans in seconds to extremely challenging ones that may take years to master (e.g., the NetHack Learning Environment). We devise fine-grained metrics to measure performance and conduct an extensive evaluation of several popular open-source and closed-source LLMs and VLMs. Our findings indicate that while current models achieve partial success in the easier games, they struggle significantly with more challenging tasks. Notably, we observe severe deficiencies in vision-based decision-making, as several models perform worse when visual representations of the environments are provided. We release BALROG as an open and user-friendly benchmark to facilitate future research and development in the agentic community. Code and Leaderboard at balrogai.com

Details

ICLR Conference 2025 Conference Paper

Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction

Anthony GX-Chen
Kenneth Marino
Rob Fergus

In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is best solved hierarchically by modelling items at a higher level of state abstraction to pixels, and attribute change at a higher level of temporal abstraction to primitive actions. This abstraction simplifies the transition dynamic by making specific future states easier to predict. We make use of this to propose a fully model-based algorithm that learns a discriminative world model, plans to explore efficiently with only a count-based intrinsic reward, and can subsequently plan to reach any discovered (abstract) states. We demonstrate the model's ability to (i) efficiently solve single tasks, (ii) transfer zero-shot and few-shot across item types and environments, and (iii) plan across long horizons. Across a suite of 2D crafting and MiniHack environments, we empirically show our model significantly out-performs state-of-the-art low-level methods (without abstraction), as well as performant model-free and model-based methods using the same abstraction. Finally, we show how to learn low level object-perturbing policies via reinforcement learning, and the object mapping itself by supervised learning.

Details

ICLR Conference 2025 Conference Paper

Training Language Models on Synthetic Edit Sequences Improves Code Synthesis

Ulyana Piterbarg
Lerrel Pinto
Rob Fergus

Software engineers mainly write code by editing existing programs. In contrast, language models (LMs) autoregressively synthesize programs in a single pass. One explanation for this is the scarcity of sequential edit data. While high-quality instruction data for code synthesis is scarce, edit data for synthesis is even scarcer. To fill this gap, we develop a synthetic data generation algorithm called LintSeq. This algorithm refactors programs into sequences of synthetic edits by using a linter to procedurally sample across interdependent lines of source code. Synthetic edits sampled with LintSeq reflect the syntax and semantics of their programming language. To test the algorithm, we use it to refactor a dataset of instruction + program pairs into instruction + program-diff-sequence tuples. Then, we fine-tune a series of smaller LMs ranging from 2.6B to 14B parameters on both the re-factored and original versions of this dataset. We perform comprehensive evaluations comparing edit sequence code LMs against baselines on HumanEval, MBPP(+), CodeContests, DS-1000, and BigCodeBench. We show that models fine-tuned to iteratively synthesize code match or outperform baselines on pass@1, and exhibit better scaling across higher pass@k as a function of total test-time FLOPs. Finally, we also pretrain our own tiny LMs for code understanding. We show that fine-tuning these models to synthesize code edit-by-edit results in strong performance on HumanEval and MBPP(+) compared to existing code language models of similar scale such as CodeT5+, AlphaCode, and Codex.

Details

NeurIPS Conference 2025 Conference Paper

Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration

Ahmed Khaled
Satyen Kale
Arthur Douillard
Chi Jin
Rob Fergus
Manzil Zaheer

Modern machine learning often requires training with large batch size, distributed data, and massively parallel compute hardware (like mobile and other edge devices or distributed data centers). Communication becomes a major bottleneck in such settings but methods like Local Stochastic Gradient Descent (Local SGD) show great promise to reduce the global communication need. Local SGD consists of three parts: a local optimization processes, an aggregation mechanism, and an outer optimizer that uses the aggregated updates from the nodes to produce a new model. While there exists an extensive literature on understanding the impact of hyperparameters in the local optimization process, the choice of outer optimizer and its hyperparameters is less clear. We study the role of the outer learning in Local SGD, and prove new convergence guarantees for the algorithm. In particular, we show that tuning the outer learning rate allows us to (a) trade off between optimization error and stochastic gradient noise variance, and (b) make up for ill-tuning of the inner learning rate. Our theory suggests that the outer learning rate should sometimes be set to values greater than $1$. We extend our results to apply to when we use momentum in the outer optimizer, and also introduce a novel data-dependent analysis of Local SGD that yields further insights on outer learning rate tuning. We conduct comprehensive experiments with standard language models and various outer optimizers to validate our theory.

PDF Details

ICML Conference 2024 Conference Paper

A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

Nicholas Monath
Will Grathwohl
Michael Boratko
Rob Fergus
Andrew McCallum
Manzil Zaheer

In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate targets (e. g. , textual passages for information retrieval). Significant challenges arise in training such encoders in the increasingly prevalent scenario of (1) a large number of targets, (2) a computationally expensive target encoder model, (3) cached target embeddings that are out-of-date due to ongoing training of target encoder parameters. This paper presents a simple and highly scalable response to these challenges by training a small parametric corrector network that adjusts stale cached target embeddings, enabling an accurate softmax approximation and thereby sampling of up-to-date high scoring "hard negatives. " We theoretically investigate the generalization properties of our proposed target corrector, relating the complexity of the network, staleness of cached representations, and the amount of training data. We present experimental results on large benchmark dense retrieval datasets as well as on QA with retrieval augmented language models. Our approach matches state-of-the-art results even when no target embedding updates are made during training beyond an initial cache from the unsupervised pre-trained model, providing a 4-80x reduction in re-embedding computational cost.

Details

ICLR Conference 2024 Conference Paper

Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders

Nishant Yadav
Nicholas Monath
Manzil Zaheer
Rob Fergus
Andrew McCallum

Cross-encoder (CE) models which compute similarity by jointly encoding a query-item pair perform better than using dot-product with embedding-based models (dual-encoders) at estimating query-item relevance. Existing approaches perform k-NN search with cross-encoders by approximating the CE similarity with a vector embedding space fit either with dual-encoders (DE) or CUR matrix factorization. DE-based retrieve-and-rerank approaches suffer from poor recall as DE generalizes poorly to new domains and the test-time retrieval with DE is decoupled from the CE. While CUR-based approaches can be more accurate than the DE-based retrieve-and-rerank approach, such approaches require a prohibitively large number of CE calls to compute item embeddings, thus making it impractical for deployment at scale. In this paper, we address these shortcomings with our proposed sparse-matrix factorization based method that efficiently computes latent query and item representations to approximate CE scores and performs k-NN search with the approximate CE similarity. In an offline indexing stage, we compute item embeddings by factorizing a sparse matrix containing query-item CE scores for a set of train queries. Our method produces a high-quality approximation while requiring only a fraction of CE similarity calls as compared to CUR-based methods, and allows for leveraging DE models to initialize the embedding space while avoiding compute- and resource-intensive finetuning of DE via distillation. At test time, we keep item embeddings fixed and perform retrieval over multiple rounds, alternating between a) estimating the test query embedding by minimizing error in approximating CE scores of items retrieved thus far, and b) using the updated test query embedding for retrieving more items in the next round. Our proposed k-NN search method can achieve up to 5 and 54 improvement in k-NN recall for k=1 and 100 respectively over the widely-used DE-based retrieve-and-rerank approach. Furthermore, our proposed approach to index the items by aligning item embeddings with the CE achieves up to 100x and 5x speedup over CUR-based and dual-encoder distillation based approaches respectively while matching or improving k-NN search recall over baselines.

Details

NeurIPS Conference 2024 Conference Paper

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Shengbang Tong
Ellis Brown
Penghao Wu
Sanghyun Woo
Manoj Middepogu
Sai C. Akula
Jihan Yang
Shusheng Yang

We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design choices for vision components are often insufficiently explored and disconnected from visual representation learning research. This gap hinders accurate sensory grounding in real-world scenarios. Our study uses LLMs and visual instruction tuning as an interface to evaluate various visual representations, offering new insights into different models and architectures—self-supervised, strongly supervised, or combinations thereof—based on experiments with over 15 vision models. We critically examine existing MLLM benchmarks, addressing the difficulties involved in consolidating and interpreting results from various tasks. To further improve visual grounding, we propose spatial vision aggregator (SVA), a dynamic and spatially-aware connector that integrates vision features with LLMs while reducing the number of tokens. Additionally, we discuss the curation of high-quality visual instruction-tuning data from publicly available sources, emphasizing the importance of distribution balancing. Collectively, Cambrian-1 not only achieves state-of-the-art performances but also serves as a comprehensive, open cookbook for instruction-tuned MLLMs. We provide model weights, code, supporting tools, datasets, and detailed instruction-tuning and evaluation recipes. We hope our release will inspire and accelerate advancements in multimodal systems and visual representation learning.

PDF Details DOI

ICML Conference 2024 Conference Paper

diff History for Neural Language Agents

Ulyana Piterbarg
Lerrel Pinto
Rob Fergus

Neural Language Models (LMs) offer an exciting solution for general-purpose embodied control. However, a key technical issue arises when using an LM-based controller: environment observations must be converted to text, which coupled with history, results in long and verbose textual prompts. As a result, prior work in LM agents is limited to restricted domains with small observation size as well as minimal needs for interaction history or instruction finetuning. In this paper, we introduce diff history, a simple and highly effective solution to these issues. By applying the Unix diff command on consecutive text observations in the interaction histories used to prompt LM policies, we can both abstract away redundant information and focus the content of textual inputs on the salient changes in the environment. On NetHack, an unsolved video game that requires long-horizon reasoning for decision-making, LMs tuned with diff history match state-of-the-art performance for neural agents while needing 1800X fewer training examples compared to prior work. Even on the simpler BabyAI-Text environment with concise text observations, we find that although diff history increases the length of prompts, the representation it provides offers a 25% improvement in the efficiency of low-sample instruction finetuning. Further, we show that diff history scales favorably across different finetuning dataset sizes. We open-source our code and data to https: //diffhistory. github. io.

Details

ICML Conference 2024 Conference Paper

USTAD: Unified Single-model Training Achieving Diverse Scores for Information Retrieval

Seungyeon Kim 0001
Ankit Singh Rawat
Manzil Zaheer
Wittawat Jitkrittum
Veeranjaneyulu Sadhanala
Sadeep Jayasumana
Aditya Krishna Menon
Rob Fergus

Modern information retrieval (IR) systems consists of multiple stages like retrieval and ranking, with Transformer-based models achieving state-of-the-art performance at each stage. In this paper, we challenge the tradition of using separate models for different stages and ask if a single Transformer encoder can provide relevance score needed in each stage. We present USTAD – a new unified approach to train a single network that can provide powerful ranking scores as a cross-encoder (CE) model as well as factorized embeddings for large-scale retrieval as a dual-encoder (DE) model. Empirically, we find a single USTAD model to be competitive to separate ranking CE and retrieval DE models. Furthermore, USTAD combines well with a novel embedding matching-based distillation, significantly improving CE to DE distillation. It further motivates novel asymmetric architectures for student models to ensure a better embedding alignment between the student and the teacher while ensuring small online inference cost. On standard benchmarks like MSMARCO, we demonstrate that USTAD with our proposed distillation method leads to asymmetric students with only 1/10th trainable parameter but retaining 95-97% of the teacher performance.

Details

ICML Conference 2023 Conference Paper

Distilling Internet-Scale Vision-Language Models into Embodied Agents

Theodore R. Sumers
Kenneth Marino
Arun Ahuja
Rob Fergus
Ishita Dasgupta 0001

Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interaction data. To address this challenge, we propose using pretrained vision-language models (VLMs) to supervise embodied agents. We combine ideas from model distillation and hindsight experience replay (HER), using a VLM to retroactively generate language describing the agent’s behavior. Simple prompting allows us to control the supervision signal, teaching an agent to interact with novel objects based on their names (e. g. , planes) or their features (e. g. , colors) in a 3D rendered environment. Fewshot prompting lets us teach abstract category membership, including pre-existing categories (food vs toys) and ad-hoc ones (arbitrary preferences over objects). Our work outlines a new and effective way to use internet-scale VLMs, repurposing the generic language grounding acquired by such models to teach task-relevant groundings to embodied agents.

Details

ICLR Conference 2023 Conference Paper

Learning About Progress From Experts

Jake Bruce
Ankit Anand
Bogdan Mazoure
Rob Fergus

Many important tasks involve some notion of long-term progress in multiple phases: e.g. to clean a shelf it must be cleared of items, cleaning products applied, and then the items placed back on the shelf. In this work, we explore the use of expert demonstrations in long-horizon tasks to learn a monotonically increasing function that summarizes progress. This function can then be used to aid agent exploration in environments with sparse rewards. As a case study we consider the NetHack environment, which requires long-term progress at a variety of scales and is far from being solved by existing approaches. In this environment, we demonstrate that by learning a model of long-term progress from expert data containing only observations, we can achieve efficient exploration in challenging sparse tasks, well beyond what is possible with current state-of-the-art approaches. We have made the curated gameplay dataset used in this work available at https://github.com/deepmind/nao_top10.

Details

NeurIPS Conference 2023 Conference Paper

NetHack is Hard to Hack

Ulyana Piterbarg
Lerrel Pinto
Rob Fergus

Neural policy learning methods have achieved remarkable results in various control problems, ranging from Atari games to simulated locomotion. However, these methods struggle in long-horizon tasks, especially in open-ended environments with multi-modal observations, such as the popular dungeon-crawler game, NetHack. Intriguingly, the NeurIPS 2021 NetHack Challenge revealed that symbolic agents outperformed neural approaches by over four times in median game score. In this paper, we delve into the reasons behind this performance gap and present an extensive study on neural policy learning for NetHack. To conduct this study, we analyze the winning symbolic agent, extending its codebase to track internal strategy selection in order to generate one of the largest available demonstration datasets. Utilizing this dataset, we examine (i) the advantages of an action hierarchy; (ii) enhancements in neural architecture; and (iii) the integration of reinforcement learning with imitation learning. Our investigations produce a state-of-the-art neural agent that surpasses previous fully neural policies by 127% in offline settings and 25% in online settings on median game score. However, we also demonstrate that mere scaling is insufficient to bridge the performance gap with the best symbolic models or even the top human players.

PDF Details

ICML Conference 2023 Conference Paper

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC

Yilun Du
Conor Durkan
Robin Strudel
Joshua B. Tenenbaum
Sander Dieleman
Rob Fergus
Jascha Sohl-Dickstein
Arnaud Doucet

Since their introduction, diffusion models have quickly become the prevailing approach to generative modeling in many domains. They can be interpreted as learning the gradients of a time-varying sequence of log-probability density functions. This interpretation has motivated classifier-based and classifier-free guidance as methods for post-hoc control of diffusion models. In this work, we build upon these ideas using the score-based interpretation of diffusion models, and explore alternative ways to condition, modify, and reuse diffusion models for tasks involving compositional generation and guidance. In particular, we investigate why certain types of composition fail using current techniques and present a number of solutions. We conclude that the sampler (not the model) is responsible for this failure and propose new samplers, inspired by MCMC, which enable successful compositional generation. Further, we propose an energy-based parameterization of diffusion models which enables the use of new compositional operators and more sophisticated, Metropolis-corrected samplers. Intriguingly we find these samplers lead to notable improvements in compositional generation across a wide variety of problems such as classifier-guided ImageNet modeling and compositional text-to-image generation.

Details

ICLR Conference 2023 Conference Paper

Teacher Guided Training: An Efficient Framework for Knowledge Transfer

Manzil Zaheer
Ankit Singh Rawat
Seungyeon Kim 0001
Chong You
Himanshu Jain
Andreas Veit
Rob Fergus
Sanjiv Kumar

The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient deployment also necessitates a large amount of (labeled or unlabeled) training data. In this paper, we propose the teacher-guided training (TGT) framework for training a high-quality compact model that leverages the knowledge acquired by pretrained generative models, while obviating the need to go through a large volume of data. TGT exploits the fact that the teacher has acquired a good representation of the underlying data domain, which typically corresponds to a much lower dimensional manifold than the input space. Furthermore, we can use the teacher to explore input space more efficiently through sampling or gradient-based methods; thus, making TGT especially attractive for limited data or long-tail settings. We formally capture this benefit of proposed data-domain exploration in our generalization bounds. We find that TGT can improve accuracy on several image classification benchmarks as well as a range of text classification and retrieval tasks.

Details

NeurIPS Conference 2022 Conference Paper

Learning to Navigate Wikipedia by Taking Random Walks

Manzil Zaheer
Kenneth Marino
Will Grathwohl
John Schultz
Wendy Shang
Sheila Babayan
Arun Ahuja
Ishita Dasgupta

A fundamental ability of an intelligent web-based agent is seeking out and acquiring new information. Internet search engines reliably find the correct vicinity but the top results may be a few links away from the desired target. A complementary approach is navigation via hyperlinks, employing a policy that comprehends local content and selects a link that moves it closer to the target. In this paper, we show that behavioral cloning of randomly sampled trajectories is sufficient to learn an effective link selection policy. We demonstrate the approach on a graph version of Wikipedia with 38M nodes and 387M edges. The model is able to efficiently navigate between nodes 5 and 20 steps apart 96% and 92% of the time, respectively. We then use the resulting embeddings and policy in downstream fact verification and question answering tasks where, in combination with basic TF-IDF search and ranking methods, they are competitive results to the state-of-the-art methods.

PDF Details

ICLR Conference 2022 Conference Paper

Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning

Denis Yarats
Rob Fergus
Alessandro Lazaric
Lerrel Pinto

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm for visual continuous control. DrQ-v2 builds on DrQ, an off-policy actor-critic approach that uses data augmentation to learn directly from pixels. We introduce several improvements that yield state-of-the-art results on the DeepMind Control Suite. Notably, DrQ-v2 is able to solve complex humanoid locomotion tasks directly from pixel observations, previously unattained by model-free RL. DrQ-v2 is conceptually simple, easy to implement, and provides significantly better computational footprint compared to prior work, with the majority of tasks taking just 8 hours to train on a single GPU. Finally, we publicly release DrQ-v2 's implementation to provide RL practitioners with a strong and computationally efficient baseline.

Details

NeurIPS Conference 2021 Conference Paper

Automatic Data Augmentation for Generalization in Reinforcement Learning

Roberta Raileanu
Maxwell Goldstein
Denis Yarats
Ilya Kostrikov
Rob Fergus

Deep reinforcement learning (RL) agents often fail to generalize beyond their training environments. To alleviate this problem, recent work has proposed the use of data augmentation. However, different tasks tend to benefit from different types of augmentations and selecting the right one typically requires expert knowledge. In this paper, we introduce three approaches for automatically finding an effective augmentation for any RL task. These are combined with two novel regularization terms for the policy and value function, required to make the use of data augmentation theoretically sound for actor-critic algorithms. Our method achieves a new state-of-the-art on the Procgen benchmark and outperforms popular RL algorithms on DeepMind Control tasks with distractors. In addition, our agent learns policies and representations which are more robust to changes in the environment that are irrelevant for solving the task, such as the background.

PDF Details

ICML Conference 2021 Conference Paper

Decoupling Value and Policy for Generalization in Reinforcement Learning

Roberta Raileanu
Rob Fergus

Standard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value function than to learn the optimal policy. Consequently, the use of a shared representation for the policy and value function can lead to overfitting. To alleviate this problem, we propose two approaches which are combined to create IDAAC: Invariant Decoupled Advantage Actor-Critic. First, IDAAC decouples the optimization of the policy and value function, using separate networks to model them. Second, it introduces an auxiliary loss which encourages the representation to be invariant to task-irrelevant properties of the environment. IDAAC shows good generalization to unseen environments, achieving a new state-of-the-art on the Procgen benchmark and outperforming popular methods on DeepMind Control tasks with distractors. Our implementation is available at https: //github. com/rraileanu/idaac.

Details

ICLR Conference 2021 Conference Paper

Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels

Denis Yarats
Ilya Kostrikov
Rob Fergus

We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages input perturbations commonly used in computer vision tasks to transform input examples, as well as regularizing the value function and policy. Existing model-free approaches, such as Soft Actor-Critic (SAC), are not able to train deep networks effectively from image pixels. However, the addition of our augmentation method dramatically improves SAC’s performance, enabling it to reach state-of-the-art performance on the DeepMind control suite, surpassing model-based (Hafner et al., 2019; Lee et al., 2019; Hafner et al., 2018) methods and recently proposed contrastive learning (Srinivas et al., 2020). Our approach, which we dub DrQ: Data-regularized Q, can be combined with any model-free reinforcement learning algorithm. We further demonstrate this by applying it to DQN and significantly improve its data-efficiency on the Atari 100k benchmark.

Details

ICML Conference 2021 Conference Paper

Imitation by Predicting Observations

Andrew Jaegle
Yury Sulsky
Arun Ahuja
Jake Bruce
Rob Fergus
Greg Wayne

Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior. Although it is easy to observe behavior in the real-world, the underlying actions may not be accessible. We present a new method for imitation solely from observations that achieves comparable performance to experts on challenging continuous control tasks while also exhibiting robustness in the presence of observations unrelated to the task. Our method, which we call FORM (for "Future Observation Reward Model") is derived from an inverse RL objective and imitates using a model of expert behavior learned by generative modelling of the expert’s observations, without needing ground truth actions. We show that FORM performs comparably to a strong baseline IRL method (GAIL) on the DeepMind Control Suite benchmark, while outperforming GAIL in the presence of task-irrelevant features.

Details

AAAI Conference 2021 Conference Paper

Improving Sample Efficiency in Model-Free Reinforcement Learning from Images

Denis Yarats
Amy Zhang
Ilya Kostrikov
Brandon Amos
Joelle Pineau
Rob Fergus

Training an agent to solve control tasks directly from highdimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy. However, fitting a high-capacity encoder using a scarce reward signal is sample inefficient and leads to poor performance. Prior work has shown that auxiliary losses, such as image reconstruction, can aid efficient representation learning. However, incorporating reconstruction loss into an offpolicy learning algorithm often leads to training instability. We explore the underlying reasons and identify variational autoencoders, used by previous investigations, as the cause of the divergence. Following these findings, we propose effective techniques to improve training stability. This results in a simple approach capable of matching state-of-the-art modelfree and model-based algorithms on MuJoCo control tasks. Furthermore, our approach demonstrates robustness to observational noise, surpassing existing approaches in this setting. Code, results, and videos are anonymously available at https: //sites. google. com/view/sac-ae/home.

PDF Details

ICML Conference 2021 Conference Paper

Offline Reinforcement Learning with Fisher Divergence Critic Regularization

Ilya Kostrikov
Rob Fergus
Jonathan Tompson
Ofir Nachum

Many modern approaches to offline Reinforcement Learning (RL) utilize behavior regularization, typically augmenting a model-free actor critic algorithm with a penalty measuring divergence of the policy from the offline data. In this work, we propose an alternative approach to encouraging the learned policy to stay close to the data, namely parameterizing the critic as the log-behavior-policy, which generated the offline data, plus a state-action value offset term, which can be learned using a neural network. Behavior regularization then corresponds to an appropriate regularizer on the offset term. We propose using a gradient penalty regularizer for the offset term and demonstrate its equivalence to Fisher divergence regularization, suggesting connections to the score matching and generative energy-based model literature. We thus term our resulting algorithm Fisher-BRC (Behavior Regularized Critic). On standard offline RL benchmarks, Fisher-BRC achieves both improved performance and faster convergence over existing state-of-the-art methods.

Details

ICML Conference 2021 Conference Paper

Reinforcement Learning with Prototypical Representations

Denis Yarats
Rob Fergus
Alessandro Lazaric
Lerrel Pinto

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent – learning a useful representation requires diverse data, while effective exploration is only possible with coherent representations. Furthermore, we would like to learn representations that not only generalize across tasks but also accelerate downstream exploration for efficient task-specific training. To address these challenges we propose Proto-RL, a self-supervised framework that ties representation learning with exploration through prototypical representations. These prototypes simultaneously serve as a summarization of the exploratory experience of an agent as well as a basis for representing observations. We pre-train these task-agnostic representations and prototypes on environments without downstream task information. This enables state-of-the-art downstream policy learning on a set of difficult continuous control tasks.

Details

ICLR Conference 2020 Conference Paper

Energy-based models for atomic-resolution protein conformations

Yilun Du
Joshua Meier
Jerry Ma
Rob Fergus
Alexander Rives

We propose an energy-based model (EBM) of protein conformations that operates at atomic scale. The model is trained solely on crystallized protein data. By contrast, existing approaches for scoring conformations use energy functions that incorporate knowledge of physical principles and features that are the complex product of several decades of research and tuning. To evaluate the model, we benchmark on the rotamer recovery task, the problem of predicting the conformation of a side chain from its context within a protein structure, which has been used to evaluate energy functions for protein design. The model achieves performance close to that of the Rosetta energy function, a state-of-the-art method widely used in protein structure prediction and design. An investigation of the model’s outputs and hidden representations finds that it captures physicochemical properties relevant to protein energy.

Details

ICML Conference 2020 Conference Paper

Fast Adaptation to New Environments via Policy-Dynamics Value Functions

Roberta Raileanu
Maxwell Goldstein
Arthur Szlam
Rob Fergus

Standard RL algorithms assume fixed environment dynamics and require a significant amount of interaction to adapt to new environments. We introduce Policy-Dynamics Value Functions (PD-VF), a novel approach for rapidly adapting to dynamics different from those previously seen in training. PD-VF explicitly estimates the cumulative reward in a space of policies and environments. An ensemble of conventional RL policies is used to gather experience on training environments, from which embeddings of both policies and environments can be learned. Then, a value function conditioned on both embeddings is trained. At test time, a few actions are sufficient to infer the environment embedding, enabling a policy to be selected by maximizing the learned value function (which requires no additional environment interaction). We show that our method can rapidly adapt to new dynamics on a set of MuJoCo domains.

Details

ICML Conference 2018 Conference Paper

Composable Planning with Attributes

Amy Zhang 0001
Sainbayar Sukhbaatar
Adam Lerer
Arthur Szlam
Rob Fergus

The tasks that an agent will need to solve often are not known during training. However, if the agent knows which properties of the environment are important then, after learning how its actions affect those properties, it may be able to use this knowledge to solve complex tasks without training specifically for them. Towards this end, we consider a setup in which an environment is augmented with a set of user defined attributes that parameterize the features of interest. We propose a method that learns a policy for transitioning between “nearby” sets of attributes, and maintains a graph of possible transitions. Given a task at test time that can be expressed in terms of a target set of attributes, and a current state, our model infers the attributes of the current state and searches over paths through attribute space to get a high level plan, and then uses its low level policy to execute the plan. We show in 3D block stacking, grid-world games, and StarCraft that our model is able to generalize to longer, more complex tasks at test time by composing simpler learned policies.

Details

ICML Conference 2018 Conference Paper

Modeling Others using Oneself in Multi-Agent Reinforcement Learning

Roberta Raileanu
Emily Denton
Arthur Szlam
Rob Fergus

We consider the multi-agent reinforcement learning setting with imperfect information. The reward function depends on the hidden goals of both agents, so the agents must infer the other players’ goals from their observed behavior in order to maximize their returns. We propose a new approach for learning in these domains: Self Other-Modeling (SOM), in which an agent uses its own policy to predict the other agent’s actions and update its belief of their hidden goal in an online manner. We evaluate this approach on three different tasks and show that the agents are able to learn better policies using their estimate of the other players’ goals, in both cooperative and competitive settings.

Details

ICML Conference 2018 Conference Paper

Stochastic Video Generation with a Learned Prior

Emily Denton
Rob Fergus

Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce a video generation model with a learned prior over stochastic latent variables at each time step. Video frames are generated by drawing samples from this prior and combining them with a deterministic estimate of the future frame. The approach is simple and easily trained end-to-end on a variety of datasets. Sample generations are both varied and sharp, even many frames into the future, and compare favorably to those from existing approaches.

Details

NeurIPS Conference 2016 Conference Paper

Learning Multiagent Communication with Backpropagation

Sainbayar Sukhbaatar
Arthur Szlam
Rob Fergus

Many tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not altered during training. In this paper we explore a simple neural model, called CommNet, that uses continuous communication for fully cooperative tasks. The model consists of multiple agents and the communication between them is learned alongside their policy. We apply this model to a diverse set of tasks, demonstrating the ability of the agents to learn to communicate amongst themselves, yielding improved performance over non-communicative agents and baselines. In some cases, it is possible to interpret the language devised by the agents, revealing simple but effective strategies for solving the task at hand.

PDF Details

ICML Conference 2016 Conference Paper

Learning Physical Intuition of Block Towers by Example

Adam Lerer
Sam Gross
Rob Fergus

Wooden blocks are a common toy for infants, allowing them to develop motor skills and gain intuition about the physical behavior of the world. In this paper, we explore the ability of deep feed-forward models to learn such intuitive physics. Using a 3D game engine, we create small towers of wooden blocks whose stability is randomized and render them collapsing (or remaining upright). This data allows us to train large convolutional network models which can accurately predict the outcome, as well as estimating the trajectories of the blocks. The models are also able to generalize in two important ways: (i) to new physical scenarios, e. g. towers with an additional block and (ii) to images of real wooden blocks, where it obtains a performance comparable to human subjects.

Details

ICML Conference 2016 Conference Paper

Learning Simple Algorithms from Examples

Wojciech Zaremba
Tomás Mikolov
Armand Joulin
Rob Fergus

We present an approach for learning simple algorithms such as copying, multi-digit addition and single digit multiplication directly from examples. Our framework consists of a set of interfaces, accessed by a controller. Typical interfaces are 1-D tapes or 2-D grids that hold the input and output data. For the controller, we explore a range of neural network-based models which vary in their ability to abstract the underlying algorithm from training instances and generalize to test examples with many thousands of digits. The controller is trained using Q-learning with several enhancements and we show that the bottleneck is in the capabilities of the controller rather than in the search incurred by Q-learning.

Details

NeurIPS Conference 2015 Conference Paper

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Emily Denton
Soumith Chintala
Arthur Szlam
Rob Fergus

In this paper we introduce a generative model capable of producing high quality samples of natural images. Our approach uses a cascade of convolutional networks (convnets) within a Laplacian pyramid framework to generate images in a coarse-to-fine fashion. At each level of the pyramid a separate generative convnet model is trained using the Generative Adversarial Nets (GAN) approach. Samples drawn from our model are of significantly higher quality than existing models. In a quantitive assessment by human evaluators our CIFAR10 samples were mistaken for real images around 40% of the time, compared to 10% for GAN samples. We also show samples from more diverse datasets such as STL10 and LSUN.

PDF Details

NeurIPS Conference 2015 Conference Paper

End-To-End Memory Networks

Sainbayar Sukhbaatar
Arthur Szlam
Jason Weston
Rob Fergus

We introduce a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network (Weston et al. , 2015) but unlike the model in that work, it is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings. It can also be seen as an extension of RNNsearch to the case where multiple computational steps (hops) are performed per output symbol. The flexibility of the model allows us to apply it to tasks as diverse as (synthetic) question answering and to language modeling. For the former our approach is competitive with Memory Networks, but with less supervision. For the latter, on the Penn TreeBank and Text8 datasets our approach demonstrates comparable performance to RNNs and LSTMs. In both cases we show that the key concept of multiple computational hops yields improved results.

PDF Details

NeurIPS Conference 2014 Conference Paper

Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

David Eigen
Christian Puhrsch
Rob Fergus

Predicting depth is an essential component in understanding the 3D geometry of a scene. While for stereo images local correspondence suffices for estimation, finding depth relations from a single image is less straightforward, requiring integration of both global and local information from various cues. Moreover, the task is inherently ambiguous, with a large source of uncertainty coming from the overall scale. In this paper, we present a new method that addresses this task by employing two deep network stacks: one that makes a coarse global prediction based on the entire image, and another that refines this prediction locally. We also apply a scale-invariant error to help measure depth relations rather than scale. By leveraging the raw datasets as large sources of training data, our method achieves state-of-the-art results on both NYU Depth and KITTI, and matches detailed depth boundaries without the need for superpixelation.

PDF Details

NeurIPS Conference 2014 Conference Paper

Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation

Emily Denton
Wojciech Zaremba
Joan Bruna
Yann LeCun
Rob Fergus

We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy, but each image evaluation requires millions of floating point operations, making their deployment on smartphones and Internet-scale clusters problematic. The computation is dominated by the convolution operations in the lower layers of the model. We exploit the redundancy present within the convolutional filters to derive approximations that significantly reduce the required computation. Using large state-of-the-art models, we demonstrate speedups of convolutional layers on both CPU and GPU by a factor of 2×, while keeping the accuracy within 1% of the original model.

PDF Details

NeurIPS Conference 2014 Conference Paper

Learning to Discover Efficient Mathematical Identities

Wojciech Zaremba
Karol Kurach
Rob Fergus

In this paper we explore how machine learning techniques can be applied to the discovery of efficient mathematical identities. We introduce an attribute grammar framework for representing symbolic expressions. Given a grammar of math operators, we build trees that combine them in different ways, looking for compositions that are analytically equivalent to a target expression but of lower computational complexity. However, as the space of trees grows exponentially with the complexity of the target expression, brute force search is impractical for all but the simplest of expressions. Consequently, we introduce two novel learning approaches that are able to learn from simpler expressions to guide the tree search. The first of these is a simple n-gram model, the other being a recursive neural-network. We show how these approaches enable us to derive complex identities, beyond reach of brute-force search, or human derivation.

PDF Details

ICLR Conference 2014 Conference Paper

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Pierre Sermanet
David Eigen
Xiang Zhang 0013
Michaël Mathieu
Rob Fergus
Yann LeCun

We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learnt simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013), and produced near state of the art results for the detection and classifications tasks. Finally, we release a feature extractor from our best model called OverFeat.

Details

ICML Conference 2013 Conference Paper

Regularization of Neural Networks using DropConnect

Li Wan 0002
Matthew D. Zeiler
Sixin Zhang
Yann LeCun
Rob Fergus

We introduce DropConnect, a generalization of DropOut, for regularizing large fully-connected layers within neural networks. When training with Dropout, a randomly selected subset of activations are set to zero within each layer. DropConnect instead sets a randomly selected subset of weights within the network to zero. Each unit thus receives input from a random subset of units in the previous layer. We derive a bound on the generalization performance of both Dropout and DropConnect. We then evaluate DropConnect on a range of datasets, comparing to Dropout, and show state-of-the-art results on several image recoginition benchmarks can be obtained by aggregating multiple DropConnect-trained models.

Details

ICLR Conference 2013 Conference Paper

Stochastic Pooling for Regularization of Deep Convolutional Neural Networks

Matthew D. Zeiler
Rob Fergus

We introduce a simple and effective method for regularizing large convolutional neural networks. We replace the conventional deterministic pooling operations with a stochastic procedure, randomly picking the activation within each pooling region according to a multinomial distribution, given by the activities within the pooling region. The approach is hyper-parameter free and can be combined with other regularization approaches, such as dropout and data augmentation. We achieve state-of-the-art performance on four image datasets, relative to other approaches that do not utilize data augmentation.

Details

NeurIPS Conference 2011 Conference Paper

Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines

Matthew Zeiler
Graham Taylor
Leonid Sigal
Iain Matthews
Rob Fergus

We present a type of Temporal Restricted Boltzmann Machine that defines a probability distribution over an output sequence conditional on an input sequence. It shares the desirable properties of RBMs: efficient exact inference, an exponentially more expressive latent state than HMMs, and the ability to model nonlinear structure and dynamics. We apply our model to a challenging real-world graphics problem: facial expression transfer. Our results demonstrate improved performance over several baselines modeling high-dimensional 2D and 3D data.

PDF Details

NeurIPS Conference 2010 Conference Paper

Pose-Sensitive Embedding by Nonlinear NCA Regression

Graham Taylor
Rob Fergus
George Williams
Ian Spiro
Christoph Bregler

This paper tackles the complex problem of visually matching people in similar pose but with different clothes, background, and other appearance changes. We achieve this with a novel method for learning a nonlinear embedding based on several extensions to the Neighborhood Component Analysis (NCA) framework. Our method is convolutional, enabling it to scale to realistically-sized images. By cheaply labeling the head and hands in large video databases through Amazon Mechanical Turk (a crowd-sourcing service), we can use the task of localizing the head and hands as a proxy for determining body pose. We apply our method to challenging real-world data and show that it can generalize beyond hand localization to infer a more general notion of body pose. We evaluate our method quantitatively against other embedding methods. We also demonstrate that real-world performance can be improved through the use of synthetic data.

PDF Details

NeurIPS Conference 2009 Conference Paper

Fast Image Deconvolution using Hyper-Laplacian Priors

Dilip Krishnan
Rob Fergus

The heavy-tailed distribution of gradients in natural scenes have proven effective priors for a range of problems such as denoising, deblurring and super-resolution. However, the use of sparse distributions makes the problem non-convex and impractically slow to solve for multi-megapixel images. In this paper we describe a deconvolution approach that is several orders of magnitude faster than existing techniques that use hyper-Laplacian priors. We adopt an alternating minimization scheme where one of the two phases is a non-convex problem that is separable over pixels. This per-pixel sub-problem may be solved with a lookup table (LUT). Alternatively, for two specific values of α, 1/2 and 2/3 an analytic solution can be found, by finding the roots of a cubic and quartic polynomial, respectively. Our approach (using either LUTs or analytic formulae) is able to deconvolve a 1 megapixel image in less than ∼3 seconds, achieving comparable quality to existing methods such as iteratively reweighted least squares (IRLS) that take ∼20 minutes. Furthermore, our method is quite general and can easily be extended to related image processing problems, beyond the deconvolution application demonstrated.

PDF Details

NeurIPS Conference 2009 Conference Paper

Semi-Supervised Learning in Gigantic Image Collections

Rob Fergus
Yair Weiss
Antonio Torralba

With the advent of the Internet it is now possible to collect hundreds of millions of images. These images come with varying degrees of label information. Clean labels can be manually obtained on a small fraction, noisy labels may be extracted automatically from surrounding text, while for most images there are no labels at all. Semi-supervised learning is a principled framework for combining these different label sources. However, it scales polynomially with the number of images, making it impractical for use on gigantic collections with hundreds of millions of images and thousands of classes. In this paper we show how to utilize recent results in machine learning to obtain highly efficient approximations for semi-supervised learning that are linear in the number of images. Specifically, we use the convergence of the eigenvectors of the normalized graph Laplacian to eigenfunctions of weighted Laplace-Beltrami operators. We combine this with a label sharing framework obtained from Wordnet to propagate label information to classes lacking manual annotations. Our algorithm enables us to apply semi-supervised learning to a database of 80 million images with 74 thousand classes.

PDF Details

NeurIPS Conference 2008 Conference Paper

Spectral Hashing

Yair Weiss
Antonio Torralba
Rob Fergus

Semantic hashing seeks compact binary codes of datapoints so that the Hamming distance between codewords correlates with semantic similarity. Hinton et al. used a clever implementation of autoencoders to find such codes. In this paper, we show that the problem of finding a best code for a given dataset is closely related to the problem of graph partitioning and can be shown to be NP hard. By relaxing the original problem, we obtain a spectral method whose solutions are simply a subset of thresh- olded eigenvectors of the graph Laplacian. By utilizing recent results on convergence of graph Laplacian eigenvectors to the Laplace-Beltrami eigen- functions of manifolds, we show how to efficiently calculate the code of a novel datapoint. Taken together, both learning the code and applying it to a novel point are extremely simple. Our experiments show that our codes significantly outperform the state-of-the art.

PDF Details

NeurIPS Conference 2007 Conference Paper

Object Recognition by Scene Alignment

Bryan Russell
Antonio Torralba
Ce Liu
Rob Fergus
William Freeman

Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve this through a simple approach: by matching the input im- age, in an appropriate representation, to images in a large training set of labeled images. Due to regularities in object identities across similar scenes, the retrieved matches provide hypotheses for object identities and locations. We build a prob- abilistic model to transfer the labels from the retrieval set to the input image. We demonstrate the effectiveness of this approach and study algorithm component contributions using held-out test sets from the LabelMe database.

PDF Details

NeurIPS Conference 2004 Conference Paper

Sampling Methods for Unsupervised Learning

Rob Fergus
Andrew Zisserman
Pietro Perona

We present an algorithm to overcome the local maxima problem in es- timating the parameters of mixture models. It combines existing ap- proaches from both EM and a robust fitting algorithm, RANSAC, to give a data-driven stochastic learning scheme. Minimal subsets of data points, sufficient to constrain the parameters of the model, are drawn from pro- posal densities to discover new regions of high likelihood. The proposal densities are learnt using EM and bias the sampling toward promising solutions. The algorithm is computationally efficient, as well as effective at escaping from local maxima. We compare it with alternative methods, including EM and RANSAC, on both challenging synthetic data and the computer vision problem of alpha-matting.

PDF Details