4.3k citations · 8.6k across the 159 of their papers we have counts for
16 papers · 1 filter
Joint inference and input optimization in equilibrium networks
Swaminathan Gurumurthy, Shaojie Bai, Zachary Manchester +1
Many tasks in deep learning involve optimizing over the \emph{inputs} to a network to minimize or maximize some objective; examples include optimization over latent spaces in a gen…
Adversarially Robust Learning for Security-Constrained Optimal Power Flow
Priya L. Donti, Aayushya Agarwal, Neeraj Vijay Bedmutha +2
In recent years, the ML community has seen surges of interest in both adversarially robust learning and implicit layers, but connections between these two areas have seldom been ex…
Boosted CVaR Classification
Runtian Zhai, Chen Dan, Arun Sai Suggala +2
Many modern machine learning tasks require models with high tail performance, i.e. high performance over the worst-off samples in the dataset. This problem has been widely studied…
Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds
Yujia Huang, Huan Zhang, Yuanyuan Shi +2
Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by…
Communicating via Markov Decision Processes
Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl +6
We consider the problem of communicating exogenous information by means of Markov decision process trajectories. This setting, which we call a Markov coding game (MCG), generalizes…
Stabilizing Equilibrium Models by Jacobian Regularization
Shaojie Bai, Vladlen Koltun, J. Zico Kolter
Deep equilibrium networks (DEQs) are a new class of models that eschews traditional depth in favor of finding the fixed point of a single nonlinear layer. These models have been sh…
DORO: Distributional and Outlier Robust Optimization
Runtian Zhai, Chen Dan, J. Zico Kolter +1
Many machine learning tasks involve subpopulation shift where the testing data distribution is a subpopulation of the training distribution. For such settings, a line of recent wor…
Assessing Generalization of SGD via Disagreement
Yiding Jiang, Vaishnavh Nagarajan, Christina Baek +1
We empirically show that the test error of deep networks can be estimated by simply training the same architecture on the same training set but with a different run of Stochastic G…
DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting
Shaoru Chen, Eric Wong, J. Zico Kolter +1
Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non-convex optimization problem, for which several past wo…
Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization
Bingqing Chen, Priya Donti, Kyri Baker +2
While reinforcement learning (RL) is gaining popularity in energy systems control, its real-world applications are limited due to the fact that the actions from learned policies ma…
RATT: Leveraging Unlabeled Data to Guarantee Generalization
Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter +1
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 th…
DC3: A learning method for optimization with hard constraints
Priya L. Donti, David Rolnick, J. Zico Kolter
Large optimization problems with hard constraints arise in many settings, yet classical solvers are often prohibitively slow, motivating the use of deep networks as cheap "approxim…
Orthogonalizing Convolutional Layers with the Cayley Transform
Asher Trockman, J. Zico Kolter
Recent work has highlighted several advantages of enforcing orthogonality in the weight layers of deep networks, such as maintaining the stability of activations, preserving gradie…
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
Jeremy M. Cohen, Simran Kaur, Yuanzhi Li +2
We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the…
On Proximal Policy Optimization's Heavy-tailed Gradients
Saurabh Garg, Joshua Zhanson, Emilio Parisotto +6
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 l…
A Bayesian Model of Cash Bail Decisions
Joshua Williams, J. Zico Kolter
The use of cash bail as a mechanism for detaining defendants pre-trial is an often-criticized system that many have argued violates the presumption of "innocent until proven guilty…