Author name cluster

Mathias Lechner

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.

32 papers

2 author rows

ICLR Conference 2025 Conference Paper

SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

Wei Xiao 0003
Tsun-Hsuan Wang
Chuang Gan 0001
Ramin M. Hasani
Mathias Lechner
Daniela Rus

Diffusion models have shown promise in data-driven planning. While these planners are commonly employed in applications where decisions are critical, they still lack established safety guarantees. In this paper, we address this limitation by introducing SafeDiffuser, a method to equip diffusion models with safety guarantees via control barrier functions. The key idea of our approach is to embed finite-time diffusion invariance, i.e., a form of specification consisting of safety constraints, into the denoising diffusion procedure. This way we enable data generation under safety constraints. We show that SafeDiffusers maintain the generative performance of diffusion models while also providing robustness in safe data generation. We evaluate our method on a series of tasks, including maze path generation, legged robot locomotion, and 3D space manipulation, and demonstrate the advantages of robustness over vanilla diffusion models.

IROS Conference 2024 Conference Paper

Competitive Multi-Team Behavior in Dynamic Flight Scenarios

Tim Seyde
Mathias Lechner
Joshua Rountree
Daniela Rus

Efficiently learning strategic multi-agent behavior remains a challenge for robotic systems deployed in real-world scenarios, especially when considering underactuated or dynamically unstable systems. Such systems demand an integrated approach that informs long-term strategic planning with constraints imposed by reactive control, and vice versa, to effectively accomplish task objectives in competitive scenarios. In this paper, we introduce a hierarchical control model to address this: a high-level controller synthesizes strategic guidance from aggregated team experiences, while a low-level controller formulates corresponding task-specific continuous controls. We apply this concept to coordination of competitive multi-team behavior in dynamic flight scenarios with F-16 aircraft. This work introduces a hierarchical reinforcement learning approach for multi-agent coordination, leveraging decoupled distributional value representations at the high-level together with goal-conditioned policy learning at the low-level, providing a control structure that integrates long-horizon strategic planning with short-horizon dynamic control. We further provide a parallel simulator for efficient learning with multi-agent F-16 dynamics.

ICML Conference 2024 Conference Paper

Large Scale Dataset Distillation with Domain Shift

Noel Loo
Alaa Maalouf
Ramin M. Hasani
Mathias Lechner
Alexander Amini
Daniela Rus

Dataset Distillation seeks to summarize a large dataset by generating a reduced set of synthetic samples. While there has been much success at distilling small datasets such as CIFAR-10 on smaller neural architectures, Dataset Distillation methods fail to scale to larger high-resolution datasets and architectures. In this work, we introduce D ataset D istillation with D omain S hift ( D3S ), a scalable distillation algorithm, made by reframing the dataset distillation problem as a domain shift one. In doing so, we derive a universal bound on the distillation loss, and provide a method for efficiently approximately optimizing it. We achieve state-of-the-art results on Tiny-ImageNet, ImageNet-1k, and ImageNet-21K over a variety of recently proposed baselines, including high cross-architecture generalization. Additionally, our ablation studies provide lessons on the importance of validation-time hyperparameters on distillation performance, motivating the need for standardization.

ICRA Conference 2024 Conference Paper

Learning with Chemical versus Electrical Synapses Does it Make a Difference?

Mónika Farsang
Mathias Lechner
David Lung
Ramin M. Hasani
Daniela Rus
Radu Grosu

Bio-inspired neural networks have the potential to advance our understanding of neural computation and improve the state-of-the-art of AI systems. Bio-electrical synapses directly transmit neural signals, by enabling fast current flow between neurons. In contrast, bio-chemical synapses transmit neural signals indirectly, through neurotransmitters. Prior work showed that interpretable dynamics for complex robotic control, can be achieved by using chemical synapses, within a sparse, bio-inspired architecture, called Neural Circuit Policies (NCPs). However, a comparison of these two synaptic models, within the same architecture, remains an unexplored area. In this work we aim to determine the impact of using chemical synapses compared to electrical synapses, in both sparse and all-to-all connected networks. We conduct experiments with autonomous lane-keeping through a photorealistic autonomous driving simulator to evaluate their performance under diverse conditions and in the presence of noise. The experiments highlight the substantial influence of the architectural and synaptic-model choices, respectively. Our results show that employing chemical synapses yields noticeable improvements compared to electrical synapses, and that NCPs lead to better results in both synaptic models.

ICLR Conference 2024 Conference Paper

Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

Neehal Tumma
Mathias Lechner
Noel Loo
Ramin M. Hasani
Daniela Rus

Developing autonomous agents that can interact with changing environments is an open challenge in machine learning. Robustness is particularly important in these settings as agents are often fit offline on expert demonstrations but deployed online where they must generalize to the closed feedback loop within the environment. In this work, we explore the application of recurrent neural networks to tasks of this nature and understand how a parameterization of their recurrent connectivity influences robustness in closed-loop settings. Specifically, we represent the recurrent connectivity as a function of rank and sparsity and show both theoretically and empirically that modulating these two variables has desirable effects on network dynamics. The proposed low-rank, sparse connectivity induces an interpretable prior on the network that proves to be most amenable for a class of models known as closed-form continuous-time neural networks (CfCs). We find that CfCs with fewer parameters can outperform their full-rank, fully-connected counterparts in the online setting under distribution shift. This yields memory-efficient and robust agents while opening a new perspective on how we can modulate network dynamics through connectivity.

ICRA Conference 2024 Conference Paper

Overparametrization helps offline-to-online generalization of closed-loop control from pixels

Mathias Lechner
Ramin M. Hasani
Alexander Amini
Tsun-Hsuan Wang
Thomas A. Henzinger
Daniela Rus

There is an ever-growing zoo of modern neural network models that can efficiently learn end-to-end control from visual observations. These advanced deep models, ranging from convolutional to Vision Transformers, from small to gigantic networks, have been extensively tested on offline image classification tasks. In this paper, we study these vision models with respect to the open-loop training to closed-loop generalization abilities, i. e. , deployment realizes a causal feedback loop that is not present during training. This causality gap typically emerges in robotics applications such as autonomous driving, where a network is trained to imitate the control commands of a human. In this setting, two situations arise: 1) Closed-loop testing in-distribution, where the test environment shares properties with those of offline training data. 2) Closed-loop testing under distribution shifts and out-of-distribution. Contrary to recently reported results, we show that under proper training guidelines, all vision architectures perform indistinguishably well on in-distribution deployment, resolving the causality gap. In situation 2, We observe that scale is the strongest factor in improving closed-loop generalization regardless of the choice of the model architecture. Our results predict the trend that in the future we will see larger and larger models being used in offline-training-online-deployment imitation learning tasks in robotic applications.

ICML Conference 2024 Conference Paper

State-Free Inference of State-Space Models: The Transfer Function Approach

Rom N. Parnichkun
Stefano Massaroli
Alessandro Moro
Jimmy T. H. Smith
Ramin M. Hasani
Mathias Lechner
Qi An
Christopher Ré

We approach designing a state-space model for deep learning applications through its dual representation, the transfer function, and uncover a highly efficient sequence parallel inference algorithm that is state-free: unlike other proposed algorithms, state-free inference does not incur any significant memory or computational cost with an increase in state size. We achieve this using properties of the proposed frequency domain transfer function parametrization, which enables direct computation of its corresponding convolutional kernel’s spectrum via a single Fast Fourier Transform. Our experimental results across multiple sequence lengths and state sizes illustrates, on average, a 35% training speed improvement over S4 layers – parametrized in time-domain – on the Long Range Arena benchmark, while delivering state-of-the-art downstream performances over other attention-free approaches. Moreover, we report improved perplexity in language modeling over a long convolutional Hyena baseline, by simply introducing our transfer function parametrization. Our code is available at https: //github. com/ruke1ire/RTF.

ICLR Conference 2024 Conference Paper

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation

Noel Loo
Ramin M. Hasani
Mathias Lechner
Alexander Amini
Daniela Rus

Modern deep learning requires large volumes of data, which could contain sensitive or private information that cannot be leaked. Recent work has shown for homogeneous neural networks a large portion of this training data could be reconstructed with only access to the trained network parameters. While the attack was shown to work empirically, there exists little formal understanding of its effective regime and which datapoints are susceptible to reconstruction. In this work, we first build a stronger version of the dataset reconstruction attack and show how it can provably recover the \emph{entire training set} in the infinite width regime. We then empirically study the characteristics of this attack on two-layer networks and reveal that its success heavily depends on deviations from the frozen infinite-width Neural Tangent Kernel limit. Next, we study the nature of easily-reconstructed images. We show that both theoretically and empirically, reconstructed images tend to ``outliers'' in the dataset, and that these reconstruction attacks can be used for \textit{dataset distillation}, that is, we can retrain on reconstructed images and obtain high predictive accuracy.

NeurIPS Conference 2023 Conference Paper

Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees

Đorđe Žikelić
Mathias Lechner
Abhinav Verma
Krishnendu Chatterjee
Thomas Henzinger

Reinforcement learning has shown promising results in learning neural network policies for complicated control tasks. However, the lack of formal guarantees about the behavior of such policies remains an impediment to their deployment. We propose a novel method for learning a composition of neural network policies in stochastic environments, along with a formal certificate which guarantees that a specification over the policy's behavior is satisfied with the desired probability. Unlike prior work on verifiable RL, our approach leverages the compositional nature of logical specifications provided in SpectRL, to learn over graphs of probabilistic reach-avoid specifications. The formal guarantees are provided by learning neural network policies together with reach-avoid supermartingales (RASM) for the graph’s sub-tasks and then composing them into a global policy. We also derive a tighter lower bound compared to previous work on the probability of reach-avoidance implied by a RASM, which is required to find a compositional policy with an acceptable probabilistic threshold for complex tasks with multiple edge policies. We implement a prototype of our approach and evaluate it on a Stochastic Nine Rooms environment.

ICML Conference 2023 Conference Paper

Dataset Distillation with Convexified Implicit Gradients

Noel Loo
Ramin M. Hasani
Mathias Lechner
Daniela Rus

We propose a new dataset distillation algorithm using reparameterization and convexification of implicit gradients (RCIG), that substantially improves the state-of-the-art. To this end, we first formulate dataset distillation as a bi-level optimization problem. Then, we show how implicit gradients can be effectively used to compute meta-gradient updates. We further equip the algorithm with a convexified approximation that corresponds to learning on top of a frozen finite-width neural tangent kernel. Finally, we improve bias in implicit gradients by parameterizing the neural network to enable analytical computation of final-layer parameters given the body parameters. RCIG establishes the new state-of-the-art on a diverse series of dataset distillation tasks. Notably, with one image per class, on resized ImageNet, RCIG sees on average a 108% improvement over the previous state-of-the-art distillation algorithm. Similarly, we observed a 66% gain over SOTA on Tiny-ImageNet and 37% on CIFAR-100.

NeurIPS Conference 2023 Conference Paper

Gigastep - One Billion Steps per Second Multi-agent Reinforcement Learning

Mathias Lechner
lianhao yin
Tim Seyde
Tsun-Hsuan Johnson Wang
Wei Xiao
Ramin Hasani
Joshua Rountree
Daniela Rus

Multi-agent reinforcement learning (MARL) research is faced with a trade-off: it either uses complex environments requiring large compute resources, which makes it inaccessible to researchers with limited resources, or relies on simpler dynamics for faster execution, which makes the transferability of the results to more realistic tasks challenging. Motivated by these challenges, we present Gigastep, a fully vectorizable, MARL environment implemented in JAX, capable of executing up to one billion environment steps per second on consumer-grade hardware. Its design allows for comprehensive MARL experimentation, including a complex, high-dimensional space defined by 3D dynamics, stochasticity, and partial observations. Gigastep supports both collaborative and adversarial tasks, continuous and discrete action spaces, and provides RGB image and feature vector observations, allowing the evaluation of a wide range of MARL algorithms. We validate Gigastep's usability through an extensive set of experiments, underscoring its role in widening participation and promoting inclusivity in the MARL research community.

ICRA Conference 2023 Conference Paper

Infrastructure-based End-to-End Learning and Prevention of Driver Failure

Noam Buckman
Shiva Sreeram
Mathias Lechner
Yutong Ban
Ramin M. Hasani
Sertac Karaman
Daniela Rus

Intelligent intersection managers can improve safety by detecting dangerous drivers or failure modes in autonomous vehicles, warning oncoming vehicles as they approach an intersection. In this work, we present FailureNet, a recurrent neural network trained end-to-end on trajectories of both nominal and reckless drivers in a scaled miniature city. FailureNet observes the poses of vehicles as they approach an intersection and detects whether a failure is present in the autonomy stack, warning cross-traffic of potentially dangerous drivers. FailureNet can accurately identify control failures, upstream perception errors, and speeding drivers, distinguishing them from nominal driving. The network is trained and deployed with autonomous vehicles in the MiniCity. Compared to speed or frequency-based predictors, FailureNet's recurrent neural network structure provides improved predictive power, yielding upwards of 84% accuracy when deployed on hardware.

AAAI Conference 2023 Conference Paper

Learning Control Policies for Stochastic Systems with Reach-Avoid Guarantees

Đorđe Žikelić
Mathias Lechner
Thomas A. Henzinger
Krishnendu Chatterjee

We study the problem of learning controllers for discrete-time non-linear stochastic dynamical systems with formal reach-avoid guarantees. This work presents the first method for providing formal reach-avoid guarantees, which combine and generalize stability and safety guarantees, with a tolerable probability threshold p in [0,1] over the infinite time horizon. Our method leverages advances in machine learning literature and it represents formal certificates as neural networks. In particular, we learn a certificate in the form of a reach-avoid supermartingale (RASM), a novel notion that we introduce in this work. Our RASMs provide reachability and avoidance guarantees by imposing constraints on what can be viewed as a stochastic extension of level sets of Lyapunov functions for deterministic systems. Our approach solves several important problems -- it can be used to learn a control policy from scratch, to verify a reach-avoid specification for a fixed control policy, or to fine-tune a pre-trained policy if it does not satisfy the reach-avoid specification. We validate our approach on 3 stochastic non-linear reinforcement learning tasks.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Liquid Structural State-Space Models

Ramin M. Hasani
Mathias Lechner
Tsun-Hsuan Wang
Makram Chahine
Alexander Amini
Daniela Rus

A proper parametrization of state transition matrices of linear state-space models (SSMs) followed by standard nonlinearities enables them to efficiently learn representations from sequential data, establishing the state-of-the-art on an extensive series of long-range sequence modeling benchmarks. In this paper, we show that we can improve further when the structured SSM, such as S4, is given by a linear liquid time-constant (LTC) state-space model. LTC neural networks are causal continuous-time neural networks with an input-dependent state transition module, which makes them learn to adapt to incoming inputs at inference. We show that by using a diagonal plus low-rank decomposition of the state transition matrix introduced in S4, and a few simplifications, the LTC-based structured state-space model, dubbed Liquid-S4, improves generalization across sequence modeling tasks with long-term dependencies such as image, text, audio, and medical time-series, with an average performance of 87.32\% on the Long-Range Arena benchmark. On the full raw Speech Command recognition dataset, Liquid-S4 achieves 96.78\% accuracy with a 30\% reduction in parameter counts compared to S4. The additional gain in performance is the direct result of the Liquid-S4's kernel structure that takes into account the similarities of the input sequence samples during training and inference.

ICML Conference 2023 Conference Paper

On the Forward Invariance of Neural ODEs

Wei Xiao 0003
Tsun-Hsuan Wang
Ramin M. Hasani
Mathias Lechner
Yutong Ban
Chuang Gan 0001
Daniela Rus

We propose a new method to ensure neural ordinary differential equations (ODEs) satisfy output specifications by using invariance set propagation. Our approach uses a class of control barrier functions to transform output specifications into constraints on the parameters and inputs of the learning system. This setup allows us to achieve output specification guarantees simply by changing the constrained parameters/inputs both during training and inference. Moreover, we demonstrate that our invariance set propagation through data-controlled neural ODEs not only maintains generalization performance but also creates an additional degree of robustness by enabling causal manipulation of the system’s parameters/inputs. We test our method on a series of representation learning tasks, including modeling physical dynamics and convexity portraits, as well as safe collision avoidance for autonomous vehicles.

NeurIPS Conference 2023 Conference Paper

On the Size and Approximation Error of Distilled Datasets

Alaa Maalouf
Murad Tukan
Noel Loo
Ramin Hasani
Mathias Lechner
Daniela Rus

Dataset Distillation is the task of synthesizing small datasets from large ones while still retaining comparable predictive accuracy to the original uncompressed dataset. Despite significant empirical progress in recent years, there is little understanding of the theoretical limitations/guarantees of dataset distillation, specifically, what excess risk is achieved by distillation compared to the original dataset, and how large are distilled datasets? In this work, we take a theoretical view on kernel ridge regression (KRR) based methods of dataset distillation such as Kernel Inducing Points. By transforming ridge regression in random Fourier features (RFF) space, we provide the first proof of the existence of small (size) distilled datasets and their corresponding excess risk for shift-invariant kernels. We prove that a small set of instances exists in the original input space such that its solution in the RFF space coincides with the solution of the original data. We further show that a KRR solution can be generated using this distilled set of instances which gives an approximation towards the KRR solution optimized on the full input data. The size of this set is linear in the dimension of the RFF space of the input set or alternatively near linear in the number of effective degrees of freedom, which is a function of the kernel, number of data points, and the regularization parameter $\lambda$. The error bound of this distilled set is also a function of $\lambda$. We verify our bounds analytically and empirically.

AAAI Conference 2023 Conference Paper

Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks

Mathias Lechner
Đorđe Žikelić
Krishnendu Chatterjee
Thomas A. Henzinger
Daniela Rus

We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore commonly adopted in industry. Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization, and certification of the quantized representation is necessary to guarantee robustness. In this work, we present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs. Inspired by advances in robust learning of non-quantized networks, our training algorithm computes the gradient of an abstract representation of the actual network. Unlike existing approaches, our method can handle the discrete semantics of QNNs. Based on QA-IBP, we also develop a complete verification procedure for verifying the adversarial robustness of QNNs, which is guaranteed to terminate and produce a correct answer. Compared to existing approaches, the key advantage of our verification procedure is that it runs entirely on GPU or other accelerator devices. We demonstrate experimentally that our approach significantly outperforms existing methods and establish the new state-of-the-art for training and certifying the robustness of QNNs.

PDF Details DOI

IROS Conference 2023 Conference Paper

Towards Cooperative Flight Control Using Visual-Attention

Lianhao Yin
Makram Chahine
Tsun-Hsuan Wang
Tim Seyde
Chao Liu 0021
Mathias Lechner
Ramin M. Hasani
Daniela Rus

The cooperation of a human pilot with an autonomous agent during flight control realizes parallel autonomy. We propose an air-guardian system that facilitates cooperation between a pilot with eye tracking and a parallel end-to-end neural control system. Our vision-based air-guardian system combines a causal continuous-depth neural network model with a cooperation layer to enable parallel autonomy between a pilot and a control system based on perceived differences in their attention profiles. The attention profiles for neural networks are obtained by computing the networks' saliency maps (feature importance) through the VisualBackProp algorithm, while the attention profiles for humans are either obtained by eye tracking of human pilots or saliency maps of networks trained to imitate human pilots. When the attention profile of the pilot and guardian agents align, the pilot makes control decisions. Otherwise, the air-guardian makes interventions and takes over the control of the aircraft. We show that our attention-based air-guardian system can balance the trade-off between its level of involvement in the flight and the pilot's expertise and attention. The guardian system is particularly effective in situations where the pilot was distracted due to information overload. We demonstrate the effectiveness of our method for navigating flight scenarios in simulation with a fixed-wing aircraft and on hardware with a quadrotor platform.

AAAI Conference 2022 Conference Paper

GoTube: Scalable Statistical Verification of Continuous-Depth Models

Sophie A. Gruenbacher
Mathias Lechner
Ramin Hasani
Daniela Rus
Thomas A. Henzinger
Scott A. Smolka
Radu Grosu

We introduce a new statistical verification algorithm that formally quantifies the behavioral robustness of any timecontinuous process formulated as a continuous-depth model. Our algorithm solves a set of global optimization (Go) problems over a given time horizon to construct a tight enclosure (Tube) of the set of all process executions starting from a ball of initial states. We call our algorithm GoTube. Through its construction, GoTube ensures that the bounding tube is conservative up to a desired probability and up to a desired tightness. GoTube is implemented in JAX and optimized to scale to complex continuous-depth neural network models. Compared to advanced reachability analysis tools for timecontinuous neural networks, GoTube does not accumulate overapproximation errors between time steps and avoids the infamous wrapping effect inherent in symbolic techniques. We show that GoTube substantially outperforms state-of-theart verification tools in terms of the size of the initial ball, speed, time-horizon, task completion, and scalability on a large set of experiments. GoTube is stable and sets the stateof-the-art in terms of its ability to scale to time horizons well beyond what has been previously possible.

ICRA Conference 2022 Conference Paper

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

Axel Brunnbauer
Luigi Berducci
Andreas Brandstätter
Mathias Lechner
Ramin M. Hasani
Daniela Rus
Radu Grosu

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e. g. , pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how such agents generalize to real-world autonomous vehicle control tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the choice of their observation model. We provide extensive empirical evidence for the effectiveness of world models provided with long enough memory horizons in sim2real tasks.

AAAI Conference 2022 Conference Paper

Stability Verification in Stochastic Control Systems via Neural Network Supermartingales

Mathias Lechner
Đorđe Žikelić
Krishnendu Chatterjee
Thomas A. Henzinger

We consider the problem of formally verifying almost-sure (a. s.) asymptotic stability in discrete-time nonlinear stochastic control systems. While verifying stability in deterministic control systems is extensively studied in the literature, verifying stability in stochastic control systems is an open problem. The few existing works on this topic either consider only specialized forms of stochasticity or make restrictive assumptions on the system, rendering them inapplicable to learning algorithms with neural network policies. In this work, we present an approach for general nonlinear stochastic control problems with two novel aspects: (a) instead of classical stochastic extensions of Lyapunov functions, we use ranking supermartingales (RSMs) to certify a. s. asymptotic stability, and (b) we present a method for learning neural network RSMs. We prove that our approach guarantees a. s. asymptotic stability of the system and provides the first method to obtain bounds on the stabilization time, which stochastic Lyapunov functions do not. Finally, we validate our approach experimentally on a set of nonlinear stochastic reinforcement learning environments with neural network policies.

ICRA Conference 2021 Conference Paper

Adversarial Training is Not Ready for Robot Learning

Mathias Lechner
Ramin M. Hasani
Radu Grosu
Daniela Rus
Thomas A. Henzinger

Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop. While adversarial training appears to enhance the robustness and safety of a deep model deployed in open-world decision-critical applications, counterintuitively, it induces undesired behaviors in robot learning settings. In this paper, we show theoretically and experimentally that neural controllers obtained via adversarial training are subjected to three types of defects, namely transient, systematic, and conditional errors. We first generalize adversarial training to a safety-domain optimization scheme allowing for more generic specifications. We then prove that such a learning process tends to cause certain error profiles. We support our theoretical results by a thorough experimental safety analysis in a robot-learning task. Our results suggest that adversarial training is not yet ready for robot learning.

NeurIPS Conference 2021 Conference Paper

Causal Navigation by Continuous-time Neural Networks

Charles Vorbach
Ramin Hasani
Alexander Amini
Mathias Lechner
Daniela Rus

Imitation learning enables high-fidelity, vision-based learning of policies within rich, photorealistic environments. However, such techniques often rely on traditional discrete-time neural models and face difficulties in generalizing to domain shifts by failing to account for the causal relationships between the agent and the environment. In this paper, we propose a theoretical and experimental framework for learning causal representations using continuous-time neural networks, specifically over their discrete-time counterparts. We evaluate our method in the context of visual-control learning of drones over a series of complex tasks, ranging from short- and long-term navigation, to chasing static and dynamic objects through photorealistic environments. Our results demonstrate that causal continuous-time deep models can perform robust navigation tasks, where advanced recurrent models fail. These models learn complex causal control representations directly from raw visual inputs and scale to solve a variety of tasks using imitation learning.

NeurIPS Conference 2021 Conference Paper

Infinite Time Horizon Safety of Bayesian Neural Networks

Mathias Lechner
Đorđe Žikelić
Krishnendu Chatterjee
Thomas Henzinger

Bayesian neural networks (BNNs) place distributions over the weights of a neural network to model uncertainty in the data and the network's prediction. We consider the problem of verifying safety when running a Bayesian neural network policy in a feedback loop with infinite time horizon systems. Compared to the existing sampling-based approaches, which are inapplicable to the infinite time horizon setting, we train a separate deterministic neural network that serves as an infinite time horizon safety certificate. In particular, we show that the certificate network guarantees the safety of the system over a subset of the BNN weight posterior's support. Our method first computes a safe weight set and then alters the BNN's weight posterior to reject samples outside this set. Moreover, we show how to extend our approach to a safe-exploration reinforcement learning setting, in order to avoid unsafe trajectories during the training of the policy. We evaluate our approach on a series of reinforcement learning benchmarks, including non-Lyapunovian safety specifications.

AAAI Conference 2021 Conference Paper

Liquid Time-constant Networks

Ramin Hasani
Mathias Lechner
Alexander Amini
Daniela Rus
Radu Grosu

We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system’s dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems modulated via nonlinear interlinked gates. The resulting models represent dynamical systems with varying (i. e. , liquid) time-constants coupled to their hidden state, with outputs being computed by numerical differential equation solvers. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations, and give rise to improved performance on time-series prediction tasks. To demonstrate these properties, we first take a theoretical approach to find bounds over their dynamics, and compute their expressive power by the trajectory length measure in a latent trajectory space. We then conduct a series of time-series prediction experiments to manifest the approximation capability of Liquid Time-Constant Networks (LTCs) compared to classical and modern RNNs.

AAAI Conference 2021 Conference Paper

On the Verification of Neural ODEs with Stochastic Guarantees

Sophie Grunbacher
Ramin Hasani
Mathias Lechner
Jacek Cyranka
Scott A. Smolka
Radu Grosu

We show that Neural ODEs, an emerging class of timecontinuous neural networks, can be verified by solving a set of global-optimization problems. For this purpose, we introduce Stochastic Lagrangian Reachability (SLR), an abstraction-based technique for constructing a tight Reachtube (an over-approximation of the set of reachable states over a given time-horizon), and provide stochastic guarantees in the form of confidence intervals for the Reachtube bounds. SLR inherently avoids the infamous wrapping effect (accumulation of over-approximation errors) by performing local optimization steps to expand safe regions instead of repeatedly forward-propagating them as is done by deterministic reachability methods. To enable fast local optimizations, we introduce a novel forward-mode adjoint sensitivity method to compute gradients without the need for backpropagation. Finally, we establish asymptotic and non-asymptotic convergence rates for SLR.

ICML Conference 2021 Conference Paper

On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification

Zahra Babaiee
Ramin M. Hasani
Mathias Lechner
Daniela Rus
Radu Grosu

Robustness to variations in lighting conditions is a key objective for any deep vision system. To this end, our paper extends the receptive field of convolutional neural networks with two residual components, ubiquitous in the visual processing system of vertebrates: On-center and off-center pathways, with an excitatory center and inhibitory surround; OOCS for short. The On-center pathway is excited by the presence of a light stimulus in its center, but not in its surround, whereas the Off-center pathway is excited by the absence of a light stimulus in its center, but not in its surround. We design OOCS pathways via a difference of Gaussians, with their variance computed analytically from the size of the receptive fields. OOCS pathways complement each other in their response to light stimuli, ensuring this way a strong edge-detection capability, and as a result an accurate and robust inference under challenging lighting conditions. We provide extensive empirical evidence showing that networks supplied with OOCS pathways gain accuracy and illumination-robustness from the novel edge representation, compared to other baselines.

AAAI Conference 2021 Conference Paper

Scalable Verification of Quantized Neural Networks

Thomas A. Henzinger
Mathias Lechner
Đorđe Žikelić

Formal verification of neural networks is an active topic of research, and recent advances have significantly increased the size of the networks that verification tools can handle. However, most methods are designed for verification of an idealized model of the actual network which works over real arithmetic and ignores rounding imprecisions. This idealization is in stark contrast to network quantization, which is a technique that trades numerical precision for computational efficiency and is, therefore, often applied in practice. Neglecting rounding errors of such low-bit quantized neural networks has been shown to lead to wrong conclusions about the network’s correctness. Thus, the desired approach for verifying quantized neural networks would be one that takes these rounding errors into account. In this paper, we show that verifying the bitexact implementation of quantized neural networks with bitvector specifications is PSPACE-hard, even though verifying idealized real-valued networks and satisfiability of bit-vector specifications alone are each in NP. Furthermore, we explore several practical heuristics toward closing the complexity gap between idealized and bit-exact verification. In particular, we propose three techniques for making SMT-based verification of quantized neural networks more scalable. Our experiments demonstrate that our proposed methods allow a speedup of up to three orders of magnitude over existing approaches.

ICML Conference 2020 Conference Paper

A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits

Ramin M. Hasani
Mathias Lechner
Alexander Amini
Daniela Rus
Radu Grosu

We propose a neural information processing system obtained by re-purposing the function of a biological neural circuit model to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce ordinary neural circuits (ONCs), defined as the model of biological neural circuits reparameterized for the control of alternative tasks. We first demonstrate that ONCs realize networks with higher maximum flow compared to arbitrary wired networks. We then learn instances of ONCs to control a series of robotic tasks, including the autonomous parking of a real-world rover robot. For reconfiguration of the purpose of the neural circuit, we adopt a search-based optimization algorithm. Ordinary neural circuits perform on par and, in some cases, significantly surpass the performance of contemporary deep learning models. ONC networks are compact, 77% sparser than their counterpart neural controllers, and their neural dynamics are fully interpretable at the cell-level.

ICRA Conference 2020 Conference Paper

Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-to-end Robot Learning Scheme

Mathias Lechner
Ramin M. Hasani
Daniela Rus
Radu Grosu

Traditional robotic control suits require profound task-specific knowledge for designing, building and testing control software. The rise of Deep Learning has enabled end-to-end solutions to be learned entirely from data, requiring minimal knowledge about the application area. We design a learning scheme to train end-to-end linear dynamical systems (LDS)s by gradient descent in imitation learning robotic domains. We introduce a new regularization loss component together with a learning algorithm that improves the stability of the learned autonomous system, by forcing the eigenvalues of the internal state updates of an LDS to be negative reals. We evaluate our approach on a series of real-life and simulated robotic experiments, in comparison to linear and nonlinear Recurrent Neural Network (RNN) architectures. Our results show that our stabilizing method significantly improves test performance of LDS, enabling such linear models to match the performance of contemporary nonlinear RNN architectures. A video of the obstacle avoidance performance of our method on a mobile robot, in unseen environments, compared to other methods can be viewed at https://youtu.be/mhEsCoNao5E.

ICLR Conference 2020 Conference Paper

Learning representations for binary-classification without backpropagation

Mathias Lechner

The family of feedback alignment (FA) algorithms aims to provide a more biologically motivated alternative to backpropagation (BP), by substituting the computations that are unrealistic to be implemented in physical brains. While FA algorithms have been shown to work well in practice, there is a lack of rigorous theory proofing their learning capabilities. Here we introduce the first feedback alignment algorithm with provable learning guarantees. In contrast to existing work, we do not require any assumption about the size or depth of the network except that it has a single output neuron, i.e., such as for binary classification tasks. We show that our FA algorithm can deliver its theoretical promises in practice, surpassing the learning performance of existing FA methods and matching backpropagation in binary classification tasks. Finally, we demonstrate the limits of our FA variant when the number of output neurons grows beyond a certain quantity.

ICRA Conference 2019 Conference Paper

Designing Worm-inspired Neural Networks for Interpretable Robotic Control

Mathias Lechner
Ramin M. Hasani
Manuel Zimmer
Thomas A. Henzinger
Radu Grosu

In this paper, we design novel liquid time-constant recurrent neural networks for robotic control, inspired by the brain of the nematode, C. elegans. In the worm's nervous system, neurons communicate through nonlinear time-varying synaptic links established amongst them by their particular wiring structure. This property enables neurons to express liquid time-constants dynamics and therefore allows the network to originate complex behaviors with a small number of neurons. We identify neuron-pair communication motifs as design operators and use them to configure compact neuronal network structures to govern sequential robotic tasks. The networks are systematically designed to map the environmental observations to motor actions, by their hierarchical topology from sensory neurons, through recurrently-wired interneurons, to motor neurons. The networks are then parametrized in a supervised-learning scheme by a search-based algorithm. We demonstrate that obtained networks realize interpretable dynamics. We evaluate their performance in controlling mobile and arm robots, and compare their attributes to other artificial neural network-based control agents. Finally, we experimentally show their superior resilience to environmental noise, compared to the existing machine learning-based methods.