4.3k citations · 8.6k across the 159 of their papers we have counts for
15 papers · 1 filter
Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games
Chun Kai Ling, J. Zico Kolter, Fei Fang
Function approximation (FA) has been a critical component in solving large zero-sum games. Yet, little attention has been given towards FA in solving \textit{general-sum} extensive…
Losses over Labels: Weakly Supervised Learning via Direct Loss Construction
Dylan Sam, J. Zico Kolter
Owing to the prohibitive costs of generating large amounts of labeled data, programmatic weak supervision is a growing paradigm within machine learning. In this setting, users desi…
Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth
Filipe de Avila Belbute-Peres, J. Zico Kolter
Neural networks with sinusoidal activations have been proposed as an alternative to networks with traditional activation functions. Despite their promise, particularly for learning…
Characterizing Datapoints via Second-Split Forgetting
Pratyush Maini, Saurabh Garg, Zachary C. Lipton +1
Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived…
Understanding the Covariance Structure of Convolutional Filters
Asher Trockman, Devin Willmott, J. Zico Kolter
Neural network weights are typically initialized at random from univariate distributions, controlling just the variance of individual weights even in highly-structured operations l…
Perfectly Secure Steganography Using Minimum Entropy Coupling
Christian Schroeder de Witt, Samuel Sokota, J. Zico Kolter +2
Steganography is the practice of encoding secret information into innocuous content in such a manner that an adversarial third party would not realize that there is hidden meaning.…
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
Huan Zhang, Shiqi Wang, Kaidi Xu +5
Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robu…
(Certified!!) Adversarial Robustness for Free!
Nicholas Carlini, Florian Tramer, Krishnamurthy Dj Dvijotham +3
In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models. To…
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Samuel Sokota, Ryan D'Orazio, J. Zico Kolter +5
This work studies an algorithm, which we call magnetic mirror descent, that is inspired by mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is dem…
Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Ameya Joshi, Minh Pham, Minsu Cho +4
Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers. However, methods based on RS require aug…
Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
Kirill Shmilovich, Devin Willmott, Ivan Batalov +3
Leveraging ab initio data at scale has enabled the development of machine learning models capable of extremely accurate and fast molecular property prediction. A central paradigm o…
Deep Equilibrium Optical Flow Estimation
Shaojie Bai, Zhengyang Geng, Yash Savani +1
Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a…
Dojo: A Differentiable Physics Engine for Robotics
Taylor A. Howell, Simon Le Cleac'h, Jan Brüdigam +5
We present Dojo, a differentiable physics engine for robotics that prioritizes stable simulation, accurate contact physics, and differentiability with respect to states, actions, a…
Patches Are All You Need?
Asher Trockman, J. Zico Kolter
Although convolutional networks have been the dominant architecture for vision tasks for many years, recent experiments have shown that Transformer-based models, most notably the V…
Understanding Why Generalized Reweighting Does Not Improve Over ERM
Runtian Zhai, Chen Dan, Zico Kolter +1
Empirical risk minimization (ERM) is known in practice to be non-robust to distributional shift where the training and the test distributions are different. A suite of approaches,…