282 citations · 376 across the 30 of their papers we have counts for
30 papers
Automatic Gradient Descent: Deep Learning without Hyperparameters
Jeremy Bernstein, Chris Mingard, Kevin Huang +2
The architecture of a deep neural network is defined explicitly in terms of the number of layers, the width of each layer and the general network topology. Existing optimisation fr…
End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions
Ryan K. Cosner, Yisong Yue, Aaron D. Ames
Imitation learning (IL) is a learning paradigm which can be used to synthesize controllers for complex systems that mimic behavior demonstrated by an expert (user or control algori…
Neurosymbolic Programming for Science
Jennifer J. Sun, Megan Tjandrasuwita, Atharva Sehgal +4
Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery. These models combine neural and symbolic components to learn complex patterns and r…
FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs
Yujia Huang, Ivan Dario Jimenez Rodriguez, Huan Zhang +2
Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also…
Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations
Yiheng Lin, James A. Preiss, Emile Anand +3
We study online adaptive policy selection in systems with time-varying costs and dynamics. We develop the Gradient-based Adaptive Policy Selection (GAPS) algorithm together with a…
Compactly Restrictable Metric Policy Optimization Problems
Victor D. Dorobantu, Kamyar Azizzadenesheli, Yisong Yue
We study policy optimization problems for deterministic Markov decision processes (MDPs) with metric state and action spaces, which we refer to as Metric Policy Optimization Proble…
MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
Jennifer J. Sun, Markus Marks, Andrew Ulmer +20
We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations. This dataset is collected from a variety o…
Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordings
Sabera Talukder, Jennifer J. Sun, Matthew Leonard +2
Neuroscientists and neuroengineers have long relied on multielectrode neural recordings to study the brain. However, in a typical experiment, many factors corrupt neural recordings…
Policy Optimization with Linear Temporal Logic Constraints
Cameron Voloshin, Hoang M. Le, Swarat Chaudhuri +1
We study the problem of policy optimization (PO) with linear temporal logic (LTL) constraints. The language of LTL allows flexible description of tasks that may be unnatural to enc…
Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds
Michael O'Connell, Guanya Shi, Xichen Shi +4
Executing safe and precise flight maneuvers in dynamic high-speed winds is important for the ongoing commoditization of uninhabited aerial vehicles (UAVs). However, because the rel…
Investigating Generalization by Controlling Normalized Margin
Alexander R. Farhang, Jeremy Bernstein, Kushal Tirumala +2
Weight norm and margin participate in learning theory via the normalized margin . Since standard neural net optimizers do not control normalized margin, it is…
Neural Gaits: Learning Bipedal Locomotion via Control Barrier Functions and Zero Dynamics Policies
Ivan Dario Jimenez Rodriguez, Noel Csomay-Shanklin, Yisong Yue +1
This work presents Neural Gaits, a method for learning dynamic walking gaits through the enforcement of set invariance that can be refined episodically using experimental data from…
MLNav: Learning to Safely Navigate on Martian Terrains
Shreyansh Daftry, Neil Abcouwer, Tyler Del Sesto +7
We present MLNav, a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as rovers navigating on Mars.…
Self-Supervised Online Learning for Safety-Critical Control using Stereo Vision
Ryan K. Cosner, Ivan D. Jimenez Rodriguez, Tamas G. Molnar +4
With the increasing prevalence of complex vision-based sensing methods for use in obstacle identification and state estimation, characterizing environment-dependent measurement err…
Safety of Sampled-Data Systems with Control Barrier Functions via Approximate Discrete Time Models
Andrew J. Taylor, Victor D. Dorobantu, Ryan K. Cosner +2
Control Barrier Functions (CBFs) have been demonstrated to be a powerful tool for safety-critical controller design for nonlinear systems. Existing design paradigms do not address…
LyaNet: A Lyapunov Framework for Training Neural ODEs
Ivan Dario Jimenez Rodriguez, Aaron D. Ames, Yisong Yue
We propose a method for training ordinary differential equations by using a control-theoretic Lyapunov condition for stability. Our approach, called LyaNet, is based on a novel Lya…
Safety-Aware Preference-Based Learning for Safety-Critical Control
Ryan K. Cosner, Maegan Tucker, Andrew J. Taylor +7
Bringing dynamic robots into the wild requires a tenuous balance between performance and safety. Yet controllers designed to provide robust safety guarantees often result in conser…
Kernel Interpolation as a Bayes Point Machine
Jeremy Bernstein, Alex Farhang, Yisong Yue
A Bayes point machine is a single classifier that approximates the majority decision of an ensemble of classifiers. This paper observes that kernel interpolation is a Bayes point m…
Natural Multicontact Walking for Robotic Assistive Devices via Musculoskeletal Models and Hybrid Zero Dynamics
Kejun Li, Maegan Tucker, Rachel Gehlhar +2
Generating stable walking gaits that yield natural locomotion when executed on robotic-assistive devices is a challenging task that often requires hand-tuning by domain experts. Th…
The Mixed-Observable Constrained Linear Quadratic Regulator Problem: the Exact Solution and Practical Algorithms
Ugo Rosolia, Yuxiao Chen, Shreyansh Daftry +3
This paper studies the problem of steering a linear time-invariant system subject to state and input constraints towards a goal location that may be inferred only through partial o…
Unsupervised Learning of Neurosymbolic Encoders
Eric Zhan, Jennifer J. Sun, Ann Kennedy +2
We present a framework for the unsupervised learning of neurosymbolic encoders, which are encoders obtained by composing neural networks with symbolic programs from a domain-specif…
Fine-Grained System Identification of Nonlinear Neural Circuits
Dawna Bagherian, James Gornet, Jeremy Bernstein +3
We study the problem of sparse nonlinear model recovery of high dimensional compositional functions. Our study is motivated by emerging opportunities in neuroscience to recover fin…
Meta-Adaptive Nonlinear Control: Theory and Algorithms
Guanya Shi, Kamyar Azizzadenesheli, Michael O'Connell +2
We present an online multi-task learning approach for adaptive nonlinear control, which we call Online Meta-Adaptive Control (OMAC). The goal is to control a nonlinear system subje…
End-to-End Sequential Sampling and Reconstruction for MRI
Tianwei Yin, Zihui Wu, He Sun +3
Accelerated MRI shortens acquisition time by subsampling in the measurement -space. Recovering a high-fidelity anatomical image from subsampled measurements requires close coope…