Author name cluster

Zachary C. Lipton

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.

34 papers

2 author rows

ICML Conference 2025 Conference Paper

Towards characterizing the value of edge embeddings in Graph Neural Networks

Dhruv Rohatgi
Tanya Marwah
Zachary C. Lipton
Jianfeng Lu 0001
Ankur Moitra
Andrej Risteski

Graph neural networks (GNNs) are the dominant approach to solving machine learning problems defined over graphs. Despite much theoretical and empirical work in recent years, our understanding of finer-grained aspects of architectural design for GNNs remains impoverished. In this paper, we consider the benefits of architectures that maintain and update edge embeddings. On the theoretical front, under a suitable computational abstraction for a layer in the model, as well as memory constraints on the embeddings, we show that there are natural tasks on graphical models for which architectures leveraging edge embeddings can be much shallower. Our techniques are inspired by results on time-space tradeoffs in theoretical computer science. Empirically, we show architectures that maintain edge embeddings almost always improve on their node-based counterparts—frequently significantly so in topologies that have "hub" nodes.

ICML Conference 2024 Conference Paper

Foundations of Testing for Finite-Sample Causal Discovery

Tom Yan
Ziyu Xu 0001
Zachary C. Lipton

Discovery of causal relationships is a fundamental goal of science and vital for sound decision making. As such, there has been considerable interest in causal discovery methods with provable guarantees. Existing works have thus far largely focused on discovery under hard intervention and infinite-samples, in which intervening on a node readily reveals the orientation of every edge incident to the node. This setup however overlooks the stochasticity inherent in real-world, finite-sample settings. Our work takes a step towards studying finite-sample causal discovery, wherein multiple interventions on a node are now needed for edge orientation. In this work, we study the canonical setup in theoretical causal discovery literature, where one assumes causal sufficiency and access to the graph skeleton. Our key observation is that discovery may be viewed as structured, multiple testing, and we develop a novel testing framework to this end. Crucially, our framework allows for anytime valid testing as multiple tests are needed to conclude an edge orientation. It also allows for flexible combination of structured test-statistics (enabling one to use Meek rules to propagate edge orientation) as well as robust testing. Through empirical simulations, we confirm the usefulness of our framework. In closing, using this testing framework, we show how one may efficiently verify graph structure by drawing a connection to multi-constraint bandits and designing a novel algorithm to this end.

NeurIPS Conference 2024 Conference Paper

Rethinking LLM Memorization through the Lens of Adversarial Compression

Avi Schwarzschild
Zhili Feng
Pratyush Maini
Zachary C. Lipton
J. Z. Kolter

Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models "memorize" all their training data or they integrate many data sources in some way more akin to how a human would learn and synthesize information. The answer hinges, to a large degree, on \emph{how we define memorization. } In this work, we propose the Adversarial Compression Ratio (ACR) as a metric for assessing memorization in LLMs. A given string from the training data is considered memorized if it can be elicited by a prompt (much) shorter than the string itself---in other words, if these strings can be ``compressed'' with the model by computing adversarial prompts of fewer tokens. The ACR overcomes the limitations of existing notions of memorization by (i) offering an adversarial view of measuring memorization, especially for monitoring unlearning and compliance; and (ii) allowing for the flexibility to measure memorization for arbitrary strings at a reasonably low compute. Our definition serves as a practical tool for determining when model owners may be violating terms around data usage, providing a potential legal tool and a critical lens through which to address such scenarios.

PDF Details DOI

ICLR Conference 2024 Conference Paper

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Pratyush Maini
Sachin Goyal
Zachary C. Lipton
J. Zico Kolter
Aditi Raghunathan

Large web-crawled multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and revolutionizing zero- and few-shot recognition. One crucial decision facing practitioners is how, if at all, to curate these ever-larger datasets. For example, the creators of the LAION-5B dataset chose to retain only image-caption pairs whose CLIP similarity score exceeded a designated threshold. In this paper, we propose a new state-of-the-art data filtering approach motivated by our observation that nearly $40\%$ of LAION's images contain text that overlaps significantly with the caption. Intuitively, such data could be wasteful as it incentivizes models to perform optical character recognition rather than learning visual features. However, naively removing all such data could also be wasteful, as it throws away images that contain visual features (in addition to overlapping text). Our simple and scalable approach, T-MARS (Text Masking and Re-Scoring), filters out only those pairs where the text dominates the remaining visual features---by first masking out the text and then filtering out those with a low CLIP similarity score of the masked image with original captions. Experimentally, T-MARS is the top ranked approach on Imagenet at ``medium scale'' of DataComp (a data filtering benchmark), and outperforms CLIP filtering by a margin of $6.5\%$ on ImageNet and $4.7\%$ on VTAB. Additionally, we show that the accuracy gains enjoyed by T-MARS linearly increase as data and compute are scaled exponentially.

NeurIPS Conference 2024 Conference Paper

The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning

Jake Fawkes
Nic Fishman
Mel Andrews
Zachary C. Lipton

Fairness metrics are a core tool in the fair machine learning literature (FairML), used to determine that ML models are, in some sense, “fair. ” Real-world data, however, are typically plagued by various measurement biases and other violatedassumptions, which can render fairness assessments meaningless. We adapt toolsfrom causal sensitivity analysis to the FairML context, providing a general frame-work which (1) accommodates effectively any combination of fairness metric andbias that can be posed in the “oblivious setting”; (2) allows researchers to inves-tigate combinations of biases, resulting in non-linear sensitivity; and (3) enablesflexible encoding of domain-specific constraints and assumptions. Employing thisframework, we analyze the sensitivity of the most common parity metrics under 3varieties of classifier across 14 canonical fairness datasets. Our analysis reveals thestriking fragility of fairness assessments to even minor dataset biases. We show thatcausal sensitivity analysis provides a powerful and necessary toolkit for gaugingthe informativeness of parity metric evaluations. Our repository is \href{https: //github. com/Jakefawkes/fragile_fair}{available here}.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Time-Varying Propensity Score to Bridge the Gap between the Past and Present

Rasool Fakoor
Jonas Mueller 0001
Zachary C. Lipton
Pratik Chaudhari
Alexander J. Smola

Real-world deployment of machine learning models is challenging because data evolves over time. While no model can work when data evolves in an arbitrary fashion, if there is some pattern to these changes, we might be able to design methods to address it. This paper addresses situations when data evolves gradually. We introduce a time-varying propensity score that can detect gradual shifts in the distribution of data which allows us to selectively sample past data to update the model---not just similar data from the past like that of a standard propensity score but also data that evolved in a similar fashion in the past. The time-varying propensity score is quite general: we demonstrate different ways of implementing it and evaluate it on a variety of problems ranging from supervised learning (e.g., image classification problems) where data undergoes a sequence of gradual shifts, to reinforcement learning tasks (e.g., robotic manipulation and continuous control) where data shifts as the policy or the task changes.

NeurIPS Conference 2024 Conference Paper

Understanding Hallucinations in Diffusion Models through Mode Interpolation

Sumukh K. Aithal
Pratyush Maini
Zachary C. Lipton
J. Z. Kolter

Colloquially speaking, image generation models based upon diffusion processes are frequently said to exhibit ''hallucinations'' samples that could never occur in the training data. But where do such hallucinations come from? In this paper, we study a particular failure mode in diffusion models, which we term mode interpolation. Specifically, we find that diffusion models smoothly ``interpolate'' between nearby data modes in the training set, to generate samples that are completely outside the support of the original training distribution; this phenomenon leads diffusion models to generate artifacts that never existed in real data (i. e. , hallucinations). We systematically study the reasons for, and the manifestation of this phenomenon. Through experiments on 1D and 2D Gaussians, we show how a discontinuous loss landscape in the diffusion model's decoder leads to a region where any smooth approximation will cause such hallucinations. Through experiments on artificial datasets with various shapes, we show how hallucination leads to the generation of combinations of shapes that never existed. We extend the validity of mode interpolation in real-world datasets by explaining the unexpected generation of images with additional or missing fingers similar to those produced by popular text-to-image generative models. Finally, we show that diffusion models in fact know when they go out of support and hallucinate. This is captured by the high variance in the trajectory of the generated sample towards the final few backward sampling process. Using a simple metric to capture this variance, we can remove over 95\% of hallucinations at generation time. We conclude our exploration by showing the implications of such hallucination (and its removal) on the collapse (and stabilization) of recursive training on synthetic data with experiments on datasets like MNIST.

PDF Details DOI

ICML Conference 2023 Conference Paper

Can Neural Network Memorization Be Localized?

Pratyush Maini
Michael Mozer
Hanie Sedghi
Zachary C. Lipton
J. Zico Kolter
Chiyuan Zhang

Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks memorize “hard” examples in the final few layers of the model. Memorization refers to the ability to correctly predict on atypical examples of the training set. In this work, we show that rather than being confined to individual layers, memorization is a phenomenon confined to a small set of neurons in various layers of the model. First, via three experimental sources of converging evidence, we find that most layers are redundant for the memorization of examples and the layers that contribute to example memorization are, in general, not the final layers. The three sources are gradient accounting (measuring the contribution to the gradient norms from memorized and clean examples), layer rewinding (replacing specific model weights of a converged model with previous training checkpoints), and retraining (training rewound layers only on clean examples). Second, we ask a more generic question: can memorization be localized anywhere in a model? We discover that memorization is often confined to a small number of neurons or channels (around 5) of the model. Based on these insights we propose a new form of dropout— example-tied dropout that enables us to direct the memorization of examples to an aprior determined set of neurons. By dropping out these neurons, we are able to reduce the accuracy on memorized examples from 100% to 3%, while also reducing the generalization gap.

ICML Conference 2023 Conference Paper

CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets

Zachary Novack
Julian J. McAuley
Zachary C. Lipton
Saurabh Garg

Open vocabulary models (e. g. CLIP) have shown strong performance on zero-shot classification through their ability generate embeddings for each class based on their (natural language) names. Prior work has focused on improving the accuracy of these models through prompt engineering or by incorporating a small amount of labeled downstream data (via finetuning). However, there has been little focus on improving the richness of the class names themselves, which can pose issues when class labels are coarsely-defined and are uninformative. We propose Classification with Hierarchical Label Sets (or CHiLS), an alternative strategy for zero-shot classification specifically designed for datasets with implicit semantic hierarchies. CHiLS proceeds in three steps: (i) for each class, produce a set of subclasses, using either existing label hierarchies or by querying GPT-3; (ii) perform the standard zero-shot CLIP procedure as though these subclasses were the labels of interest; (iii) map the predicted subclass back to its parent to produce the final prediction. Across numerous datasets with underlying hierarchical structure, CHiLS leads to improved accuracy in situations both with and without ground-truth hierarchical information. CHiLS is simple to implement within existing zero-shot pipelines and requires no additional training cost. Code is available at: https: //github. com/acmi-lab/CHILS.

ICLR Conference 2023 Conference Paper

Disentangling the Mechanisms Behind Implicit Regularization in SGD

Zachary Novack
Simran Kaur 0001
Tanya Marwah
Saurabh Garg
Zachary C. Lipton

A number of competing hypotheses have been proposed to explain why small-batch Stochastic Gradient Descent (SGD) leads to improved generalization over the full-batch regime, with recent work crediting the implicit regularization of various quantities throughout training. However, to date, empirical evidence assessing the explanatory power of these hypotheses is lacking. In this paper, we conduct an extensive empirical evaluation, focusing on the ability of various theorized mechanisms to close the small-to-large batch generalization gap. Additionally, we characterize how the quantities that SGD has been claimed to (implicitly) regularize change over the course of training. By using micro-batches, i.e. disjoint smaller subsets of each mini-batch, we empirically show that explicitly penalizing the gradient norm or the Fisher Information Matrix trace, averaged over micro-batches, in the large-batch regime recovers small-batch SGD generalization, whereas Jacobian-based regularizations fail to do so. This generalization performance is shown to often be correlated with how well the regularized model’s gradient norms resemble those of small-batch SGD. We additionally show that this behavior breaks down as the micro-batch size approaches the batch size. Finally, we note that in this line of inquiry, positive experimental findings on CIFAR10 are often reversed on other datasets like CIFAR100, highlighting the need to test hypotheses on a wider collection of datasets.

AAAI Conference 2023 Conference Paper

Moral Machine or Tyranny of the Majority?

Michael Feffer
Hoda Heidari
Zachary C. Lipton

With artificial intelligence systems increasingly applied in consequential domains, researchers have begun to ask how AI systems ought to act in ethically charged situations where even humans lack consensus. In the Moral Machine project, researchers crowdsourced answers to "Trolley Problems" concerning autonomous vehicles. Subsequently, Noothigattu et al. (2018) proposed inferring linear functions that approximate each individual's preferences and aggregating these linear models by averaging parameters across the population. In this paper, we examine this averaging mechanism, focusing on fairness concerns and strategic effects. We investigate a simple setting where the population consists of two groups, the minority constitutes an α < 0.5 share of the population, and within-group preferences are homogeneous. Focusing on the fraction of contested cases where the minority group prevails, we make the following observations: (a) even when all parties report their preferences truthfully, the fraction of disputes where the minority prevails is less than proportionate in α; (b) the degree of sub-proportionality grows more severe as the level of disagreement between the groups increases; (c) when parties report preferences strategically, pure strategy equilibria do not always exist; and (d) whenever a pure strategy equilibrium exists, the majority group prevails 100% of the time. These findings raise concerns about stability and fairness of averaging as a mechanism for aggregating diverging voices. Finally, we discuss alternatives, including randomized dictatorship and median-based mechanisms.

PDF Details DOI

ICML Conference 2023 Conference Paper

Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective

Tanya Marwah
Zachary C. Lipton
Jianfeng Lu 0001
Andrej Risteski

A burgeoning line of research has developed deep neural networks capable of approximating the solutions to high dimensional PDEs, opening related lines of theoretical inquiry focused on explaining how it is that these models appear to evade the curse of dimensionality. However, most theoretical analyses thus far have been limited to linear PDEs. In this work, we take a step towards studying the representational power of neural networks for approximating solutions to nonlinear PDEs. We focus on a class of PDEs known as nonlinear elliptic variational PDEs, whose solutions minimize an Euler-Lagrange energy functional $\mathcal{E}(u) = \int_\Omega L(x, u(x), \nabla u(x)) - f(x) u(x)dx$. We show that if composing a function with Barron norm $b$ with partial derivatives of $L$ produces a function of Barron norm at most $B_L b^p$, the solution to the PDE can be $\epsilon$-approximated in the $L^2$ sense by a function with Barron norm $O\left(\left(dB_L\right)^{\max\{p \log(1/ \epsilon), p^{\log(1/\epsilon)}\}}\right)$. By a classical result due to Barron (1993), this correspondingly bounds the size of a 2-layer neural network needed to approximate the solution. Treating $p, \epsilon, B_L$ as constants, this quantity is polynomial in dimension, thus showing neural networks can evade the curse of dimensionality. Our proof technique involves neurally simulating (preconditioned) gradient in an appropriate Hilbert space, which converges exponentially fast to the solution of the PDE, and such that we can bound the increase of the Barron norm at each iterate. Our results subsume and substantially generalize analogous prior results for linear elliptic PDEs over a unit hypercube.

UAI Conference 2023 Conference Paper

Risk-limiting financial audits via weighted sampling without replacement

Shubhanshu Shekhar
Ziyu Xu 0001
Zachary C. Lipton
Pierre J. Liang
Aaditya Ramdas

We introduce the notion of risk-limiting financial audits (RLFA): procedures that manually evaluate a subset of $N$ financial transactions to check the validity of a claimed assertion $\mathcal{A}$ about the transactions. More specifically, RLFA satisfy two properties: (i) if $\mathcal{A}$ is false, they correctly disprove it with probability at least $1-\delta$, and (ii) they validate the correctness of $\mathcal{A}$ with probability $1$, if it is true. We propose a general RLFA strategy, by constructing new confidence sequences (CSs) for the weighted average of $N$ unknown values, based on samples drawn without replacement from a (randomized) weighted sampling scheme. Next, we develop methods to improve the quality of CSs by incorporating side information about the unknown values. We show that when the side information is sufficiently accurate, it can directly drive the sampling. For the case where the accuracy is unknown a priori, we introduce an alternative approach using control variates. Crucially, our construction adapts to the quality of side information by strongly leveraging the side information if it is highly predictive, and learning to ignore it if it is uninformative. Our methods also recover the state-of-the-art bounds for the special case of uniformly sampled observations with no side information, which has already found applications in election auditing. The harder weighted case with general side information solves the more challenging problem of AI-assisted financial auditing.

ICML Conference 2023 Conference Paper

RLSbench: Domain Adaptation Under Relaxed Label Shift

Saurabh Garg
Nick Erickson
James Sharpnack
Alexander J. Smola
Sivaraman Balakrishnan
Zachary C. Lipton

Despite the emergence of principled methods for domain adaptation under label shift, their sensitivity to shifts in class conditional distributions is precariously under explored. Meanwhile, popular deep domain adaptation heuristics tend to falter when faced with label proportions shifts. While several papers modify these heuristics in attempts to handle label proportions shifts, inconsistencies in evaluation standards, datasets, and baselines make it difficult to gauge the current best practices. In this paper, we introduce RLSbench, a large-scale benchmark for relaxed label shift, consisting of $>$500 distribution shift pairs spanning vision, tabular, and language modalities, with varying label proportions. Unlike existing benchmarks, which primarily focus on shifts in class-conditional $p(x|y)$, our benchmark also focuses on label marginal shifts. First, we assess 13 popular domain adaptation methods, demonstrating more widespread failures under label proportion shifts than were previously known. Next, we develop an effective two-step meta-algorithm that is compatible with most domain adaptation heuristics: (i) pseudo-balance the data at each epoch; and (ii) adjust the final classifier with target label distribution estimate. The meta-algorithm improves existing domain adaptation heuristics under large label proportion shifts, often by 2–10% accuracy points, while conferring minimal effect ($<$0. 5%) when label proportions do not shift. We hope that these findings and the availability of RLSbench will encourage researchers to rigorously evaluate proposed methods in relaxed label shift settings. Code is publicly available at https: //github. com/acmi-lab/RLSbench.

AAAI Conference 2022 Conference Paper

Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations

Siddhant Arora
Danish Pruthi
Norman Sadeh
William W. Cohen
Zachary C. Lipton
Graham Neubig

In attempts to “explain” predictions of machine learning models, researchers have proposed hundreds of techniques for attributing predictions to features that are deemed important. While these attributions are often claimed to hold the potential to improve human “understanding” of the models, surprisingly little work explicitly evaluates progress towards this aspiration. In this paper, we conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. They are challenged both to simulate the model on fresh reviews, and to edit reviews with the goal of lowering the probability of the originally predicted class. Successful manipulations would lead to an adversarial example. During the training (but not the test) phase, input spans are highlighted to communicate salience. Through our evaluation, we observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control. For the BERT-based classifier, popular local explanations do not improve their ability to reduce the model confidence over the no-explanation case. Remarkably, when the explanation for the BERT model is given by the (global) attributions of a linear model trained to imitate the BERT model, people can effectively manipulate the model.

ICLR Conference 2022 Conference Paper

Leveraging unlabeled data to predict out-of-distribution performance

Saurabh Garg
Sivaraman Balakrishnan
Zachary C. Lipton
Behnam Neyshabur
Hanie Sedghi

Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a \emph{threshold} on the model's confidence, predicting accuracy as the fraction of unlabeled examples for which model confidence exceeds that threshold. ATC outperforms previous methods across several model architectures, types of distribution shifts (e.g., due to synthetic corruptions, dataset reproduction, or novel subpopulations), and datasets (\textsc{Wilds}-FMoW, ImageNet, \breeds, CIFAR, and MNIST). In our experiments, ATC estimates target performance $2\text{--}4\times$ more accurately than prior methods. We also explore the theoretical foundations of the problem, proving that, in general, identifying the accuracy is just as hard as identifying the optimal predictor and thus, the efficacy of any method rests upon (perhaps unstated) assumptions on the nature of the shift. Finally, analyzing our method on some toy distributions, we provide insights concerning when it works.

AAAI Conference 2022 Conference Paper

Modeling Attrition in Recommender Systems with Departing Bandits

Omer Ben-Porat
Lee Cohen
Liu Leqi
Zachary C. Lipton
Yishay Mansour

Traditionally, when recommender systems are formalized as multi-armed bandits, the policy of the recommender system influences the rewards accrued, but not the length of interaction. However, in real-world systems, dissatisfied users may depart (and never come back). In this work, we propose a novel multiarmed bandit setup that captures such policy-dependent horizons. Our setup consists of a finite set of user types, and multiple arms with Bernoulli payoffs. Each (user type, arm) tuple corresponds to an (unknown) reward probability. Each user’s type is initially unknown and can only be inferred through their response to recommendations. Moreover, if a user is dissatisfied with their recommendation, they might depart the system. We first address the case where all users share the same type, demonstrating that a recent UCB-based algorithm is optimal. We then move forward to the more challenging case, where users are divided among two types. While naive approaches cannot handle this setting, we provide an efficient learning algorithm that achieves Õ( √ T) regret, where T is the number of users.

ICML Conference 2022 Conference Paper

Supervised Learning with General Risk Functionals

Liu Leqi
Audrey Huang
Zachary C. Lipton
Kamyar Azizzadenesheli

Standard uniform convergence results bound the generalization gap of the expected loss over a hypothesis class. The emergence of risk-sensitive learning requires generalization guarantees for functionals of the loss distribution beyond the expectation. While prior works specialize in uniform convergence of particular functionals, our work provides uniform convergence for a general class of Hölder risk functionals for which the closeness in the Cumulative Distribution Function (CDF) entails closeness in risk. We establish the first uniform convergence results for estimating the CDF of the loss distribution, which yield uniform convergence guarantees that hold simultaneously both over a class of Hölder risk functionals and over a hypothesis class. Thus licensed to perform empirical risk minimization, we develop practical gradient-based methods for minimizing distortion risks (widely studied subset of Hölder risks that subsumes the spectral risks, including the mean, conditional value at risk, cumulative prospect theory risks, and others) and provide convergence guarantees. In experiments, we demonstrate the efficacy of our learning procedure, both in settings where uniform convergence results hold and in high-dimensional settings with deep networks.

ICML Conference 2021 Conference Paper

Correcting Exposure Bias for Link Recommendation

Shantanu Gupta
Hao Wang 0014
Zachary C. Lipton
Yuyang Wang 0001

Link prediction methods are frequently applied in recommender systems, e. g. , to suggest citations for academic papers or friends in social networks. However, exposure bias can arise when users are systematically underexposed to certain relevant items. For example, in citation networks, authors might be more likely to encounter papers from their own field and thus cite them preferentially. This bias can propagate through naively trained link predictors, leading to both biased evaluation and high generalization error (as assessed by true relevance). Moreover, this bias can be exacerbated by feedback loops. We propose estimators that leverage known exposure probabilities to mitigate this bias and consequent feedback loops. Next, we provide a loss function for learning the exposure probabilities from data. Finally, experiments on semi-synthetic data based on real-world citation networks, show that our methods reliably identify (truly) relevant citations. Additionally, our methods lead to greater diversity in the recommended papers’ fields of study. The code is available at github. com/shantanu95/exposure-bias-link-rec.

UAI Conference 2021 Conference Paper

Estimating treatment effects with observed confounders and mediators

Shantanu Gupta
Zachary C. Lipton
David Childers

Given a causal graph, the do-calculus can express treatment effects as functionals of the observational joint distribution that can be estimated empirically. Sometimes the do-calculus identifies multiple valid formulae, prompting us to compare the statistical properties of the corresponding estimators. For example, the backdoor formula applies when all confounders are observed and the frontdoor formula applies when an observed mediator transmits the causal effect. In this paper, we investigate the over-identified scenario where both confounders and mediators are observed, rendering both estimators valid. Addressing the linear Gaussian causal model, we demonstrate that either estimator can dominate the other by an unbounded constant factor. Next, we derive an optimal estimator, which leverages all observed variables, and bound its finite-sample variance. We show that it strictly outperforms the backdoor and frontdoor estimators and that this improvement can be unbounded. We also present a procedure for combining two datasets, one with observed confounders and another with observed mediators. Finally, we evaluate our methods on both simulated data and the IHDP and JTPA datasets.

ICLR Conference 2021 Conference Paper

Explaining the Efficacy of Counterfactually Augmented Data

Divyansh Kaushik
Amrith Setlur
Eduard H. Hovy
Zachary C. Lipton

In attempts to produce machine learning models less reliant on spurious patterns in NLP datasets, researchers have recently proposed curating counterfactually augmented data (CAD) via a human-in-the-loop process in which given some documents and their (initial) labels, humans must revise the text to make a counterfactual label applicable. Importantly, edits that are not necessary to flip the applicable label are prohibited. Models trained on the augmented (original and revised) data appear, empirically, to rely less on semantically irrelevant words and to generalize better out of domain. While this work draws loosely on causal thinking, the underlying causal model (even at an abstract level) and the principles underlying the observed out-of-domain improvements remain unclear. In this paper, we introduce a toy analog based on linear Gaussian models, observing interesting relationships between causal models, measurement noise, out-of-domain generalization, and reliance on spurious signals. Our analysis provides some insights that help to explain the efficacy of CAD. Moreover, we develop the hypothesis that while adding noise to causal features should degrade both in-domain and out-of-domain performance, adding noise to non-causal features should lead to relative improvements in out-of-domain performance. This idea inspires a speculative test for determining whether a feature attribution technique has identified the causal spans. If adding noise (e.g., by random word flips) to the highlighted spans degrades both in-domain and out-of-domain performance on a battery of challenge datasets, but adding noise to the complement gives improvements out-of-domain, this suggests we have identified causal spans. Thus, we present a large scale empirical study comparing spans edited to create CAD to those selected by attention and saliency maps. Across numerous challenge domains and models, we find that the hypothesized phenomenon is pronounced for CAD.

ICML Conference 2021 Conference Paper

On Proximal Policy Optimization's Heavy-tailed Gradients

Saurabh Garg
Joshua Zhanson
Emilio Parisotto
Adarsh Prasad
J. Zico Kolter
Zachary C. Lipton
Sivaraman Balakrishnan
Ruslan Salakhutdinov

Modern policy gradient algorithms such as Proximal Policy Optimization (PPO) rely on an arsenal of heuristics, including loss clipping and gradient clipping, to ensure successful learning. These heuristics are reminiscent of techniques from robust statistics, commonly used for estimation in outlier-rich ("heavy-tailed") regimes. In this paper, we present a detailed empirical study to characterize the heavy-tailed nature of the gradients of the PPO surrogate reward function. We demonstrate that the gradients, especially for the actor network, exhibit pronounced heavy-tailedness and that it increases as the agent’s policy diverges from the behavioral policy (i. e. , as the agent goes further off policy). Further examination implicates the likelihood ratios and advantages in the surrogate reward as the main sources of the observed heavy-tailedness. We then highlight issues arising due to the heavy-tailed nature of the gradients. In this light, we study the effects of the standard PPO clipping heuristics, demonstrating that these tricks primarily serve to offset heavy-tailedness in gradients. Thus motivated, we propose incorporating GMOM, a high-dimensional robust estimator, into PPO as a substitute for three clipping tricks. Despite requiring less hyperparameter tuning, our method matches the performance of PPO (with all heuristics enabled) on a battery of MuJoCo continuous control tasks.

ICML Conference 2021 Conference Paper

RATT: Leveraging Unlabeled Data to Guarantee Generalization

Saurabh Garg
Sivaraman Balakrishnan
J. Zico Kolter
Zachary C. Lipton

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk; or (ii) validate empirically on holdout data. However, (i) typically yields vacuous guarantees for overparameterized models; and (ii) shrinks the training set and its guarantee erodes with each re-use of the holdout set. In this paper, we leverage unlabeled data to produce generalization bounds. After augmenting our (labeled) training set with randomly labeled data, we train in the standard fashion. Whenever classifiers achieve low error on the clean data but high error on the random data, our bound ensures that the true risk is low. We prove that our bound is valid for 0-1 empirical risk minimization and with linear classifiers trained by gradient descent. Our approach is especially useful in conjunction with deep learning due to the early learning phenomenon whereby networks fit true labels before noisy labels but requires one intuitive assumption. Empirically, on canonical computer vision and NLP tasks, our bound provides non-vacuous generalization guarantees that track actual performance closely. This work enables practitioners to certify generalization even when (labeled) holdout data is unavailable and provides insights into the relationship between random label noise and generalization.

AAAI Conference 2021 Conference Paper

Symbolic Music Generation with Transformer-GANs

Aashiq Muhamed
Liang Li
Xingjian Shi
Suri Yaddanapudi
Wayne Chi
Dylan Jackson
Rahul Suresh
Zachary C. Lipton

Autoregressive models using Transformers have emerged as the dominant approach for music generation with the goal of synthesizing minute-long compositions that exhibit largescale musical structure. These models are commonly trained by minimizing the negative log-likelihood (NLL) of the observed sequence in an autoregressive manner. Unfortunately, the quality of samples from these models tends to degrade significantly for long sequences, a phenomenon attributed to exposure bias. Fortunately, we are able to detect these failures with classifiers trained to distinguish between real and sampled sequences, an observation that motivates our exploration of adversarial losses to complement the NLL objective. We use a pre-trained Span-BERT model for the discriminator of the GAN, which in our experiments helped with training stability. We use the Gumbel-Softmax trick to obtain a differentiable approximation of the sampling process. This makes discrete sequences amenable to optimization in GANs. In addition, we break the sequences into smaller chunks to ensure that we stay within a given memory budget. We demonstrate via human evaluations and a new discriminative metric that the music generated by our approach outperforms a baseline trained with likelihood maximization, the state-of-the-art Music Transformer, and other GANs used for sequence generation. 57% of people prefer music generated via our approach while 43% prefer Music Transformer.

ICLR Conference 2020 Conference Paper

Learning The Difference That Makes A Difference With Counterfactually-Augmented Data

Divyansh Kaushik
Eduard H. Hovy
Zachary C. Lipton

Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due to confounding (e.g., a common cause), but not direct or indirect causal effects. In this paper, we focus on natural language processing, introducing methods and resources for training models less sensitive to spurious patterns. Given documents and their initial labels, we task humans with revising each document so that it (i) accords with a counterfactual target label; (ii) retains internal coherence; and (iii) avoids unnecessary changes. Interestingly, on sentiment analysis and natural language inference tasks, classifiers trained on original data fail on their counterfactually-revised counterparts and vice versa. Classifiers trained on combined datasets perform remarkably well, just shy of those specialized to either domain. While classifiers trained on either original or manipulated data alone are sensitive to spurious features (e.g., mentions of genre), models trained on the combined data are less sensitive to this signal. Both datasets are publicly available.

JMLR Journal 2020 Journal Article

Tensor Regression Networks

Jean Kossaifi
Zachary C. Lipton
Arinbjorn Kolbeinsson
Aran Khanna
Tommaso Furlanello
Anima Anandkumar

Convolutional neural networks typically consist of many convolutional layers followed by one or more fully connected layers. While convolutional layers map between high-order activation tensors, the fully connected layers operate on flattened activation vectors. Despite empirical success, this approach has notable drawbacks. Flattening followed by fully connected layers discards multilinear structure in the activations and requires many parameters. We address these problems by incorporating tensor algebraic operations that preserve multilinear structure at every layer. First, we introduce Tensor Contraction Layers (TCLs) that reduce the dimensionality of their input while preserving their multilinear structure using tensor contraction. Next, we introduce Tensor Regression Layers (TRLs), which express outputs through a low-rank multilinear mapping from a high-order activation tensor to an output tensor of arbitrary order. We learn the contraction and regression factors end-to-end, and produce accurate nets with fewer parameters. Additionally, our layers regularize networks by imposing low-rank constraints on the activations (TCL) and regression weights (TRL). Experiments on ImageNet show that, applied to VGG and ResNet architectures, TCLs and TRLs reduce the number of parameters compared to fully connected layers by more than 65% while maintaining or increasing accuracy. In addition to the space savings, our approach's ability to leverage topological structure can be crucial for structured data such as MRI. In particular, we demonstrate significant performance improvements over comparable architectures on three tasks associated with the UK Biobank dataset. [abs] [ pdf ][ bib ] &copy JMLR 2020. ( edit, beta )

ICML Conference 2020 Conference Paper

Uncertainty-Aware Lookahead Factor Models for Quantitative Investing

Lakshay Chauhan
John Alberg
Zachary C. Lipton

On a periodic basis, publicly traded companies report fundamentals, financial data including revenue, earnings, debt, among others. Quantitative finance research has identified several factors, functions of the reported data that historically correlate with stock market performance. In this paper, we first show through simulation that if we could select stocks via factors calculated on future fundamentals (via oracle), that our portfolios would far outperform standard factor models. Motivated by this insight, we train deep nets to forecast future fundamentals from a trailing 5-year history. We propose lookahead factor models which plug these predicted future fundamentals into traditional factors. Finally, we incorporate uncertainty estimates from both neural heteroscedastic regression and a dropout-based heuristic, improving performance by adjusting our portfolios to avert risk. In retrospective analysis, we leverage an industry-grade portfolio simulator (backtester) to show simultaneous improvement in annualized return and Sharpe ratio. Specifically, the simulated annualized return for the uncertainty-aware model is 17. 7% (vs 14. 0% for a standard factor model) and the Sharpe ratio is 0. 84 (vs 0. 52).

IJCAI Conference 2019 Conference Paper

AmazonQA: A Review-Based Question Answering Task

Mansi Gupta
Nitish Kulkarni
Raghuveer Chanda
Anirudha Rayasam
Zachary C. Lipton

Every day, thousands of customers post questions on Amazon product pages. After some time, if they are fortunate, a knowledgeable customer might answer their question. Observing that many questions can be answered based upon the available product reviews, we propose the task of review-based QA. Given a corpus of reviews and a question, the QA system synthesizes an answer. To this end, we introduce a new dataset and propose a method that combines informational retrieval techniques for selecting relevant reviews (given a question) and "reading comprehension" models for synthesizing an answer (given a question and review). Our dataset consists of 923k questions, 3. 6M answers and 14M reviews across 156k products. Building on the well-known Amazon dataset, we additionally collect annotations marking each question as either answerable or unanswerable based on the available reviews. A deployed system could first classify a question as answerable before attempting to generate a provisional answer. Notably, unlike many popular QA datasets, here the questions, passages, and answers are extracted from real human interactions. We evaluate a number of models for answer generation and propose strong baselines, demonstrating the challenging nature of this new task.

ICML Conference 2019 Conference Paper

Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment

Yifan Wu
Ezra Winston
Divyansh Kaushik
Zachary C. Lipton

Domain adaptation addresses the common situation in which the target distribution generating our test data differs from the source distribution generating our training data. While absent assumptions, domain adaptation is impossible, strict conditions, e. g. covariate or label shift, enable principled algorithms. Recently-proposed domain-adversarial approaches consist of aligning source and target encodings, an approach often motivated as minimizing two (of three) terms in a theoretical bound on target error. Unfortunately, this minimization can cause arbitrary increases in the third term, a problem guaranteed to arise under shifting label distributions. We propose asymmetrically-relaxed distribution alignment, a new approach that overcomes some limitations of standard domain-adversarial algorithms. Moreover, we characterize precise assumptions under which our algorithm is theoretically principled and demonstrate empirical benefits on both synthetic and real datasets.

ICLR Conference 2019 Conference Paper

Learning Robust Representations by Projecting Superficial Statistics Out

Haohan Wang
Zexue He
Zachary C. Lipton
Eric P. Xing

Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under distribution shift. For example, subtle changes to the background or texture of an image can break a seemingly powerful classifier. Building on previous work on domain generalization, we hope to produce a classifier that will generalize to previously unseen domains, even when domain identifiers are not available during training. This setting is challenging because the model may extract many distribution-specific (superficial) signals together with distribution-agnostic (semantic) signals. To overcome this challenge, we incorporate the gray-level co-occurrence matrix (GLCM) to extract patterns that our prior knowledge suggests are superficial: they are sensitive to the texture but unable to capture the gestalt of an image. Then we introduce two techniques for improving our networks' out-of-sample performance. The first method is built on the reverse gradient method that pushes our model to learn representations from which the GLCM representation is not predictable. The second method is built on the independence introduced by projecting the model's representation onto the subspace orthogonal to GLCM representation's. We test our method on the battery of standard domain generalization data sets and, interestingly, achieve comparable or better performance as compared to other domain generalization methods that explicitly require samples from the target distribution for training.

ICML Conference 2019 Conference Paper

What is the Effect of Importance Weighting in Deep Learning?

Jonathon Byrd
Zachary C. Lipton

Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is well-characterized for low-capacity misspecified models, little is known about how it impacts over-parameterized, deep neural networks. This work is inspired by recent theoretical results showing that on (linearly) separable data, deep linear networks optimized by SGD learn weight-agnostic solutions, prompting us to ask, for realistic deep networks, for which many practical datasets are separable, what is the effect of importance weighting? We present the surprising finding that while importance weighting impacts models early in training, its effect diminishes over successive epochs. Moreover, while L2 regularization and batch normalization (but not dropout), restore some of the impact of importance weighting, they express the effect via (seemingly) the wrong abstraction: why should practitioners tweak the L2 regularization, and by how much, to produce the correct weighting effect? Our experiments confirm these findings across a range of architectures and datasets.

ICML Conference 2018 Conference Paper

Born-Again Neural Networks

Tommaso Furlanello
Zachary C. Lipton
Michael Tschannen
Laurent Itti
Anima Anandkumar

Knowledge Distillation (KD) consists of transferring “knowledge” from one machine learning model (the teacher) to another (the student). Commonly, the teacher is a high-capacity model with formidable performance, while the student is more compact. By transferring knowledge, one hopes to benefit from the student’s compactness, without sacrificing too much performance. We study KD from a new perspective: rather than compressing models, we train students parameterized identically to their teachers. Surprisingly, these Born-Again Networks (BANs), outperform their teachers significantly, both on computer vision and language modeling tasks. Our experiments with BANs based on DenseNets demonstrate state-of-the-art performance on the CIFAR-10 (3. 5%) and CIFAR-100 (15. 5%) datasets, by validation error. Additional experiments explore two distillation objectives: (i) Confidence-Weighted by Teacher Max (CWTM) and (ii) Dark Knowledge with Permuted Predictions (DKPP). Both methods elucidate the essential components of KD, demonstrating the effect of the teacher outputs on both predicted and non-predicted classes.

ICML Conference 2018 Conference Paper

Detecting and Correcting for Label Shift with Black Box Predictors

Zachary C. Lipton
Yu-Xiang Wang 0003
Alexander J. Smola

Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets), cause symptoms (observations), we focus on label shift, where the label marginal p(y) changes but the conditional p(x| y) does not. We propose Black Box Shift Estimation (BBSE) to estimate the test distribution p(y). BBSE exploits arbitrary black box predictors to reduce dimensionality prior to shift correction. While better predictors give tighter estimates, BBSE works even when predictors are biased, inaccurate, or uncalibrated, so long as their confusion matrices are invertible. We prove BBSE’s consistency, bound its error, and introduce a statistical test that uses BBSE to detect shift. We also leverage BBSE to correct classifiers. Experiments demonstrate accurate estimates and improved prediction, even on high-dimensional datasets of natural images.

ICML Conference 2017 Conference Paper

Dance Dance Convolution

Chris Donahue
Zachary C. Lipton
Julian J. McAuley

Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players perform steps on a dance platform in synchronization with music as directed by on-screen step charts. While many step charts are available in standardized packs, players may grow tired of existing charts, or wish to dance to a song for which no chart exists. We introduce the task of learning to choreograph. Given a raw audio track, the goal is to produce a new step chart. This task decomposes naturally into two subtasks: deciding when to place steps and deciding which steps to select. For the step placement task, we combine recurrent and convolutional neural networks to ingest spectrograms of low-level audio features to predict steps, conditioned on chart difficulty. For step selection, we present a conditional LSTM generative model that substantially outperforms n-gram and fixed-window approaches.