Search Results for author: J Zico Kolter

Found 17 papers, 3 papers with code

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

1 code implementation NeurIPS 2021 Yujia Huang, huan zhang, Yuanyuan Shi, J Zico Kolter, Anima Anandkumar

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 computing a global bound on its Lipschitz constant.

Understanding Overfitting in Reweighting Algorithms for Worst-group Performance

no code implementations29 Sep 2021 Runtian Zhai, Chen Dan, J Zico Kolter, Pradeep Kumar Ravikumar

Prior work has proposed various reweighting algorithms to improve the worst-group performance of machine learning models for fairness.

Data Augmentation Fairness

A Fine-Tuning Approach to Belief State Modeling

no code implementations ICLR 2022 Samuel Sokota, Hengyuan Hu, David J Wu, J Zico Kolter, Jakob Nicolaus Foerster, Noam Brown

Furthermore, because this specialization occurs after the action or policy has already been decided, BFT does not require the belief model to process it as input.

Generative Posterior Networks for Approximately Bayesian Epistemic Uncertainty Estimation

no code implementations29 Sep 2021 Melrose Roderick, Felix Berkenkamp, Fatemeh Sheikholeslami, J Zico Kolter

Ensembles of neural networks are often used to estimate epistemic uncertainty in high-dimensional problems because of their scalability and ease of use.

Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation

no code implementations ICLR 2022 Colin Wei, J Zico Kolter

Our key insights are that these interval bounds can be obtained as the fixed-point solution to an IBP-inspired equilibrium equation, and furthermore, that this solution always exists and is unique when the layer obeys a certain parameterization.

A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks

no code implementations29 Sep 2021 huan zhang, Shiqi Wang, Kaidi Xu, Yihan Wang, Suman Jana, Cho-Jui Hsieh, J Zico Kolter

In this work, we formulate an adversarial attack using a branch-and-bound (BaB) procedure on ReLU neural networks and search adversarial examples in the activation space corresponding to binary variables in a mixed integer programming (MIP) formulation.

Adversarial Attack

Monotone deep Boltzmann machines

no code implementations29 Sep 2021 Zhili Feng, Ezra Winston, J Zico Kolter

In this paper, we propose a class of model that allows for \emph{exact, efficient} mean-field inference and learning in \emph{general} deep Boltzmann machines.

Neural Deep Equilibrium Solvers

no code implementations ICLR 2022 Shaojie Bai, Vladlen Koltun, J Zico Kolter

A deep equilibrium (DEQ) model abandons traditional depth by solving for the fixed point of a single nonlinear layer $f_\theta$.

Model-based Reinforcement Learning with Ensembled Model-value Expansion

no code implementations29 Sep 2021 Gaurav Manek, J Zico Kolter

Model-based reinforcement learning (MBRL) methods are often more data-efficient and quicker to converge than their model-free counterparts, but typically rely crucially on accurate modeling of the environment dynamics and associated uncertainty in order to perform well.

Model-based Reinforcement Learning reinforcement-learning

Empirical robustification of pre-trained classifiers

no code implementations ICML Workshop AML 2021 Mohammad Sadegh Norouzzadeh, Wan-Yi Lin, Leonid Boytsov, Leslie Rice, huan zhang, Filipe Condessa, J Zico Kolter

Most pre-trained classifiers, though they may work extremely well on the domain they were trained upon, are not trained in a robust fashion, and therefore are sensitive to adversarial attacks.

Denoising Image Reconstruction +1

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification

no code implementations NeurIPS 2021 Shiqi Wang, huan zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, J Zico Kolter

We develop $\beta$-CROWN, a new bound propagation based method that can fully encode neuron split constraints in branch-and-bound (BaB) based complete verification via optimizable parameters $\beta$.

Estimating Lipschitz constants of monotone deep equilibrium models

no code implementations ICLR 2021 Chirag Pabbaraju, Ezra Winston, J Zico Kolter

Several methods have been proposed in recent years to provide bounds on the Lipschitz constants of deep networks, which can be used to provide robustness guarantees, generalization bounds, and characterize the smoothness of decision boundaries.

Generalization Bounds

Provably robust classification of adversarial examples with detection

1 code implementation ICLR 2021 Fatemeh Sheikholeslami, Ali Lotfi, J Zico Kolter

Adversarial attacks against deep networks can be defended against either by building robust classifiers or, by creating classifiers that can \emph{detect} the presence of adversarial perturbations.

Classification General Classification +1

On the Neural Tangent Kernel of Equilibrium Models

no code implementations1 Jan 2021 Zhili Feng, J Zico Kolter

Existing analyses of the neural tangent kernel (NTK) for infinite-depth networks show that the kernel typically becomes degenerate as the number of layers grows.

Multiplicative Filter Networks

2 code implementations ICLR 2021 Rizal Fathony, Anit Kumar Sahu, Devin Willmott, J Zico Kolter

Although deep networks are typically used to approximate functions over high dimensional inputs, recent work has increased interest in neural networks as function approximators for low-dimensional-but-complex functions, such as representing images as a function of pixel coordinates, solving differential equations, or representing signed distance fields or neural radiance fields.

Certified robustness against physically-realizable patch attack via randomized cropping

no code implementations1 Jan 2021 Wan-Yi Lin, Fatemeh Sheikholeslami, Jinghao Shi, Leslie Rice, J Zico Kolter

Our method improves upon the current state of the art in defending against patch attacks on CIFAR10 and ImageNet, both in terms of certified accuracy and inference time.

Classification Crop Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.