Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDJ. Zico Kolter
Zico Kolter – Jeremy Z. Kolter
Person information
- affiliation: Carnegie Mellon University, PA, USA
- affiliation (former): MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[j8]Zhili Feng, Ezra Winston, J. Zico Kolter:
Monotone deep Boltzmann machines. Trans. Mach. Learn. Res. 2023 (2023)- [j7]Asher Trockman, J. Zico Kolter:
Patches Are All You Need? Trans. Mach. Learn. Res. 2023 (2023) - [c134]Chun Kai Ling, J. Zico Kolter, Fei Fang:
Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games. AAAI 2023: 5764-5772 - [c133]Dylan Sam, J. Zico Kolter:
Losses over Labels: Weakly Supervised Learning via Direct Loss Construction. AAAI 2023: 9695-9703 - [c132]Sina Baharlouei, Fatemeh Sheikholeslami, Meisam Razaviyayn, Zico Kolter:
Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes. AISTATS 2023: 11059-11078 - [c131]Mingjie Sun, Zico Kolter:
Single Image Backdoor Inversion via Robust Smoothed Classifiers. CVPR 2023: 8113-8122 - [c130]Sachin Goyal, Ananya Kumar, Sankalp Garg, Zico Kolter, Aditi Raghunathan:
Finetune like you pretrain: Improved finetuning of zero-shot vision models. CVPR 2023: 19338-19347 - [c129]Filipe de Avila Belbute-Peres, J. Zico Kolter:
Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth. ICLR 2023 - [c128]Nicholas Carlini, Florian Tramèr, Krishnamurthy (Dj) Dvijotham, Leslie Rice, Mingjie Sun, J. Zico Kolter:
(Certified!!) Adversarial Robustness for Free! ICLR 2023 - [c127]Samuel Sokota, Ryan D'Orazio, J. Zico Kolter, Nicolas Loizou, Marc Lanctot, Ioannis Mitliagkas, Noam Brown, Christian Kroer:
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games. ICLR 2023 - [c126]Asher Trockman, Devin Willmott, J. Zico Kolter:
Understanding the Covariance Structure of Convolutional Filters. ICLR 2023 - [c125]Christian Schröder de Witt, Samuel Sokota, J. Zico Kolter, Jakob Nicolaus Foerster, Martin Strohmeier:
Perfectly Secure Steganography Using Minimum Entropy Coupling. ICLR 2023 - [c124]Runtian Zhai, Chen Dan, J. Zico Kolter, Pradeep Kumar Ravikumar:
Understanding Why Generalized Reweighting Does Not Improve Over ERM. ICLR 2023 - [c123]Pratyush Maini, Michael Curtis Mozer, Hanie Sedghi, Zachary Chase Lipton, J. Zico Kolter, Chiyuan Zhang:
Can Neural Network Memorization Be Localized? ICML 2023: 23536-23557 - [c122]Samuel Sokota, Ryan D'Orazio, Chun Kai Ling, David J. Wu, J. Zico Kolter, Noam Brown:
Abstracting Imperfect Information Away from Two-Player Zero-Sum Games. ICML 2023: 32169-32193 - [c121]Asher Trockman, J. Zico Kolter:
Mimetic Initialization of Self-Attention Layers. ICML 2023: 34456-34468 - [c120]Swaminathan Gurumurthy, Zachary Manchester, J. Zico Kolter:
Practical Critic Gradient based Actor Critic for On-Policy Reinforcement Learning. L4DC 2023: 625-638 - [c119]Swaminathan Gurumurthy, J. Zico Kolter, Zachary Manchester:
Deep Off-Policy Iterative Learning Control. L4DC 2023: 639-652 - [c118]Rahul Venkatesh, Eric Wong, Zico Kolter:
Adversarial robustness in discontinuous spaces via alternating sampling & descent. WACV 2023: 4651-4660 - [i125]Samuel Sokota, Ryan D'Orazio, Chun Kai Ling, David J. Wu, J. Zico Kolter, Noam Brown:
Abstracting Imperfect Information Away from Two-Player Zero-Sum Games. CoRR abs/2301.09159 (2023) - [i124]Suhas Kotha, Christopher Brix, Zico Kolter, Krishnamurthy Dvijotham, Huan Zhang:
Provably Bounding Neural Network Preimages. CoRR abs/2302.01404 (2023) - [i123]Allan Zhou, Kaien Yang, Kaylee Burns, Yiding Jiang, Samuel Sokota, J. Zico Kolter, Chelsea Finn:
Permutation Equivariant Neural Functionals. CoRR abs/2302.14040 (2023) - [i122]Mingjie Sun, Zico Kolter:
Single Image Backdoor Inversion via Robust Smoothed Classifiers. CoRR abs/2303.00215 (2023) - [i121]Mrigank Raman, Pratyush Maini, J. Zico Kolter, Zachary C. Lipton, Danish Pruthi:
Model-tuning Via Prompts Makes NLP Models Adversarially Robust. CoRR abs/2303.07320 (2023) - [i120]Mukul Bhutani, J. Zico Kolter:
Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport. CoRR abs/2303.07675 (2023) - [i119]Rattana Pukdee, Dylan Sam, J. Zico Kolter, Maria-Florina Balcan, Pradeep Ravikumar:
Learning with Explanation Constraints. CoRR abs/2303.14496 (2023) - [i118]Paul Vicol, Zico Kolter, Kevin Swersky:
Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single. CoRR abs/2304.11153 (2023) - [i117]Samuel Sokota, Gabriele Farina, David J. Wu, Hengyuan Hu, Kevin A. Wang, J. Zico Kolter, Noam Brown:
The Update Equivalence Framework for Decision-Time Planning. CoRR abs/2304.13138 (2023) - [i116]Asher Trockman, J. Zico Kolter:
Mimetic Initialization of Self-Attention Layers. CoRR abs/2305.09828 (2023) - [i115]Allan Zhou, Kaien Yang, Yiding Jiang, Kaylee Burns, Winnie Xu, Samuel Sokota, J. Zico Kolter, Chelsea Finn:
Neural Functional Transformers. CoRR abs/2305.13546 (2023) - [i114]Runtian Zhai, Bingbin Liu, Andrej Risteski, Zico Kolter, Pradeep Ravikumar:
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation. CoRR abs/2306.00788 (2023) - [i113]Yiding Jiang, Christina Baek, J. Zico Kolter:
On the Joint Interaction of Models, Data, and Features. CoRR abs/2306.04793 (2023) - [i112]Yiding Jiang, J. Zico Kolter, Roberta Raileanu:
On the Importance of Exploration for Generalization in Reinforcement Learning. CoRR abs/2306.05483 (2023) - [i111]Mingjie Sun, Zhuang Liu, Anna Bair, J. Zico Kolter:
A Simple and Effective Pruning Approach for Large Language Models. CoRR abs/2306.11695 (2023) - [i110]Hariharan Manikandan, Yiding Jiang, J. Zico Kolter:
Language models are weak learners. CoRR abs/2306.14101 (2023) - [i109]Yutong He, Ruslan Salakhutdinov, J. Zico Kolter:
Localized Text-to-Image Generation for Free via Cross Attention Control. CoRR abs/2306.14636 (2023) - [i108]Pratyush Maini, Sachin Goyal, Zachary C. Lipton, J. Zico Kolter, Aditi Raghunathan:
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning. CoRR abs/2307.03132 (2023) - [i107]Zhili Feng, Anna Bair, J. Zico Kolter:
Leveraging Multiple Descriptive Features for Robust Few-shot Image Learning. CoRR abs/2307.04317 (2023) - [i106]Zhili Feng, Ezra Winston, J. Zico Kolter:
Monotone deep Boltzmann machines. CoRR abs/2307.04990 (2023) - [i105]Varun Shankar, Shivam Barwey, Zico Kolter, Romit Maulik, Venkatasubramanian Viswanathan:
Importance of equivariant and invariant symmetries for fluid flow modeling. CoRR abs/2307.05486 (2023) - [i104]Pratyush Maini, Michael C. Mozer, Hanie Sedghi, Zachary C. Lipton, J. Zico Kolter, Chiyuan Zhang:
Can Neural Network Memorization Be Localized? CoRR abs/2307.09542 (2023) - [i103]Andy Zou, Zifan Wang, J. Zico Kolter, Matt Fredrikson:
Universal and Transferable Adversarial Attacks on Aligned Language Models. CoRR abs/2307.15043 (2023) - [i102]Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, Dan Hendrycks:
Representation Engineering: A Top-Down Approach to AI Transparency. CoRR abs/2310.01405 (2023) - [i101]Victor Akinwande, Yiding Jiang, Dylan Sam, J. Zico Kolter:
Understanding prompt engineering may not require rethinking generalization. CoRR abs/2310.03957 (2023) - [i100]Eungyeup Kim, Mingjie Sun, Aditi Raghunathan, Zico Kolter:
Reliable Test-Time Adaptation via Agreement-on-the-Line. CoRR abs/2310.04941 (2023) - [i99]Zhili Feng, J. Zico Kolter:
On the Neural Tangent Kernel of Equilibrium Models. CoRR abs/2310.14062 (2023) - [i98]Zhengyang Geng, J. Zico Kolter:
TorchDEQ: A Library for Deep Equilibrium Models. CoRR abs/2310.18605 (2023) - 2022
- [c117]Shaojie Bai, Zhengyang Geng, Yash Savani, J. Zico Kolter:
Deep Equilibrium Optical Flow Estimation. CVPR 2022: 610-620 - [c116]Nadine Behrmann, S. Alireza Golestaneh, Zico Kolter, Jürgen Gall, Mehdi Noroozi:
Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation. ECCV (35) 2022: 52-68 - [c115]Shaojie Bai, Vladlen Koltun, J. Zico Kolter:
Neural Deep Equilibrium Solvers. ICLR 2022 - [c114]Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, J. Zico Kolter:
Assessing Generalization of SGD via Disagreement. ICLR 2022 - [c113]Samuel Sokota, Hengyuan Hu, David J. Wu, J. Zico Kolter, Jakob Nicolaus Foerster, Noam Brown:
A Fine-Tuning Approach to Belief State Modeling. ICLR 2022 - [c112]Colin Wei, J. Zico Kolter:
Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation. ICLR 2022 - [c111]Samuel Sokota, Christian A. Schröder de Witt, Maximilian Igl, Luisa M. Zintgraf, Philip H. S. Torr, Martin Strohmeier, J. Zico Kolter, Shimon Whiteson, Jakob N. Foerster:
Communicating via Markov Decision Processes. ICML 2022: 20314-20328 - [c110]Huan Zhang, Shiqi Wang, Kaidi Xu, Yihan Wang, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter:
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks. ICML 2022: 26591-26604 - [c109]Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, J. Zico Kolter, Roger B. Grosse:
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation. NeurIPS 2022 - [c108]Christina Baek, Yiding Jiang, Aditi Raghunathan, J. Zico Kolter:
Agreement-on-the-line: Predicting the Performance of Neural Networks under Distribution Shift. NeurIPS 2022 - [c107]Sachin Goyal, Mingjie Sun, Aditi Raghunathan, J. Zico Kolter:
Test Time Adaptation via Conjugate Pseudo-labels. NeurIPS 2022 - [c106]Yiding Jiang, Evan Zheran Liu, Benjamin Eysenbach, J. Zico Kolter, Chelsea Finn:
Learning Options via Compression. NeurIPS 2022 - [c105]Pratyush Maini, Saurabh Garg, Zachary C. Lipton, J. Zico Kolter:
Characterizing Datapoints via Second-Split Forgetting. NeurIPS 2022 - [c104]Gaurav Manek, J. Zico Kolter:
The Pitfalls of Regularization in Off-Policy TD Learning. NeurIPS 2022 - [c103]Ashwini Pokle, Zhengyang Geng, J. Zico Kolter:
Deep Equilibrium Approaches to Diffusion Models. NeurIPS 2022 - [c102]Zhouxing Shi, Yihan Wang, Huan Zhang, J. Zico Kolter, Cho-Jui Hsieh:
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation. NeurIPS 2022 - [c101]Huan Zhang, Shiqi Wang, Kaidi Xu, Linyi Li, Bo Li, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter:
General Cutting Planes for Bound-Propagation-Based Neural Network Verification. NeurIPS 2022 - [i97]Asher Trockman, J. Zico Kolter:
Patches Are All You Need? CoRR abs/2201.09792 (2022) - [i96]Runtian Zhai
, Chen Dan, J. Zico Kolter, Pradeep Ravikumar:
Understanding Why Generalized Reweighting Does Not Improve Over ERM. CoRR abs/2201.12293 (2022) - [i95]Taylor A. Howell, Simon Le Cleac'h, J. Zico Kolter, Mac Schwager, Zachary Manchester:
Dojo: A Differentiable Simulator for Robotics. CoRR abs/2203.00806 (2022) - [i94]Shaojie Bai, Zhengyang Geng, Yash Savani, J. Zico Kolter:
Deep Equilibrium Optical Flow Estimation. CoRR abs/2204.08442 (2022) - [i93]Ameya Joshi, Minh Pham, Minsu Cho, Leonid Boytsov, Filipe Condessa, J. Zico Kolter, Chinmay Hegde:
Smooth-Reduce: Leveraging Patches for Improved Certified Robustness. CoRR abs/2205.06154 (2022) - [i92]Samuel Sokota, Ryan D'Orazio, J. Zico Kolter, Nicolas Loizou, Marc Lanctot, Ioannis Mitliagkas, Noam Brown, Christian Kroer:
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games. CoRR abs/2206.05825 (2022) - [i91]Nicholas Carlini, Florian Tramèr, Krishnamurthy Dvijotham, J. Zico Kolter:
(Certified!!) Adversarial Robustness for Free! CoRR abs/2206.10550 (2022) - [i90]Karren Yang, Wan-Yi Lin, Manash Barman, Filipe Condessa, J. Zico Kolter:
Defending Multimodal Fusion Models against Single-Source Adversaries. CoRR abs/2206.12714 (2022) - [i89]Christina Baek, Yiding Jiang, Aditi Raghunathan, Zico Kolter:
Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift. CoRR abs/2206.13089 (2022) - [i88]Sachin Goyal, Mingjie Sun, Aditi Raghunathan, Zico Kolter:
Test-Time Adaptation via Conjugate Pseudo-labels. CoRR abs/2207.09640 (2022) - [i87]Huan Zhang, Shiqi Wang, Kaidi Xu, Linyi Li, Bo Li, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter:
General Cutting Planes for Bound-Propagation-Based Neural Network Verification. CoRR abs/2208.05740 (2022) - [i86]Nadine Behrmann, S. Alireza Golestaneh, Zico Kolter, Juergen Gall, Mehdi Noroozi:
Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation. CoRR abs/2209.00638 (2022) - [i85]Asher Trockman, Devin Willmott, J. Zico Kolter:
Understanding the Covariance Structure of Convolutional Filters. CoRR abs/2210.03651 (2022) - [i84]Zhouxing Shi, Yihan Wang, Huan Zhang, J. Zico Kolter, Cho-Jui Hsieh:
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation. CoRR abs/2210.07394 (2022) - [i83]Ashwini Pokle, Zhengyang Geng, Zico Kolter:
Deep Equilibrium Approaches to Diffusion Models. CoRR abs/2210.12867 (2022) - [i82]Sina Baharlouei, Fatemeh Sheikholeslami, Meisam Razaviyayn, Zico Kolter:
Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes. CoRR abs/2210.14410 (2022) - [i81]Christian Schröder de Witt, Samuel Sokota, J. Zico Kolter, Jakob N. Foerster, Martin Strohmeier:
Perfectly Secure Steganography Using Minimum Entropy Coupling. CoRR abs/2210.14889 (2022) - [i80]Pratyush Maini, Saurabh Garg, Zachary C. Lipton, J. Zico Kolter:
Characterizing Datapoints via Second-Split Forgetting. CoRR abs/2210.15031 (2022) - [i79]Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, Zico Kolter, Roger B. Grosse:
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation. CoRR abs/2211.09961 (2022) - [i78]Filipe de Avila Belbute-Peres, J. Zico Kolter:
Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth. CoRR abs/2211.14503 (2022) - [i77]Sachin Goyal, Ananya Kumar, Sankalp Garg, Zico Kolter, Aditi Raghunathan:
Finetune like you pretrain: Improved finetuning of zero-shot vision models. CoRR abs/2212.00638 (2022) - [i76]Yiding Jiang, Evan Zheran Liu, Benjamin Eysenbach, Zico Kolter, Chelsea Finn:
Learning Options via Compression. CoRR abs/2212.04590 (2022) - [i75]Dylan Sam, J. Zico Kolter:
Losses over Labels: Weakly Supervised Learning via Direct Loss Construction. CoRR abs/2212.06921 (2022) - [i74]Chun Kai Ling, J. Zico Kolter, Fei Fang:
Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games. CoRR abs/2212.14431 (2022) - 2021
- [c100]Melrose Roderick, Vaishnavh Nagarajan, J. Zico Kolter:
Provably Safe PAC-MDP Exploration Using Analogies. AISTATS 2021: 1216-1224 - [c99]Karren Yang, Wan-Yi Lin, Manash Barman, Filipe Condessa, J. Zico Kolter:
Defending Multimodal Fusion Models Against Single-Source Adversaries. CVPR 2021: 3340-3349 - [c98]Leonid Boytsov, Zico Kolter:
Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits. ECIR (1) 2021: 63-78 - [c97]Bingqing Chen, Priya L. Donti, Kyri Baker, J. Zico Kolter, Mario Bergés:
Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization. e-Energy 2021: 199-210 - [c96]Joshua Williams, J. Zico Kolter:
A Bayesian Model of Cash Bail Decisions. FAccT 2021: 827-837 - [c95]Eric Wong, J. Zico Kolter:
Learning perturbation sets for robust machine learning. ICLR 2021 - [c94]Jeremy Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter, Ameet Talwalkar:
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability. ICLR 2021 - [c93]Priya L. Donti, Melrose Roderick, Mahyar Fazlyab, J. Zico Kolter:
Enforcing robust control guarantees within neural network policies. ICLR 2021 - [c92]Priya L. Donti, David Rolnick, J. Zico Kolter:
DC3: A learning method for optimization with hard constraints. ICLR 2021 - [c91]Rizal Fathony, Anit Kumar Sahu, Devin Willmott, J. Zico Kolter:
Multiplicative Filter Networks. ICLR 2021 - [c90]Chirag Pabbaraju, Ezra Winston, J. Zico Kolter:
Estimating Lipschitz constants of monotone deep equilibrium models. ICLR 2021 - [c89]Fatemeh Sheikholeslami, Ali Lotfi, J. Zico Kolter:
Provably robust classification of adversarial examples with detection. ICLR 2021 - [c88]Asher Trockman, J. Zico Kolter:
Orthogonalizing Convolutional Layers with the Cayley Transform. ICLR 2021 - [c87]Shaojie Bai, Vladlen Koltun, J. Zico Kolter:
Stabilizing Equilibrium Models by Jacobian Regularization. ICML 2021: 554-565 - [c86]Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter, Zachary C. Lipton:
RATT: Leveraging Unlabeled Data to Guarantee Generalization. ICML 2021: 3598-3609 - [c85]Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Zachary C. Lipton, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Pradeep Ravikumar:
On Proximal Policy Optimization's Heavy-tailed Gradients. ICML 2021: 3610-3619 - [c84]Runtian Zhai, Chen Dan, J. Zico Kolter, Pradeep Ravikumar:
DORO: Distributional and Outlier Robust Optimization. ICML 2021: 12345-12355 - [c83]Satya Narayan Shukla, Anit Kumar Sahu, Devin Willmott, J. Zico Kolter:
Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes. KDD 2021: 1461-1469 - [c82]Zhichun Huang, Shaojie Bai, J. Zico Kolter:
$(\textrm{Implicit})^2$: Implicit Layers for Implicit Representations. NeurIPS 2021: 9639-9650 - [c81]Swaminathan Gurumurthy, Shaojie Bai, Zachary Manchester, J. Zico Kolter:
Joint inference and input optimization in equilibrium networks. NeurIPS 2021: 16818-16832 - [c80]Samuel Sokota, Caleb Ho, Zaheen Farraz Ahmad, J. Zico Kolter:
Monte Carlo Tree Search With Iteratively Refining State Abstractions. NeurIPS 2021: 18698-18709 - [c79]Runtian Zhai, Chen Dan, Arun Sai Suggala, J. Zico Kolter, Pradeep Ravikumar:
Boosted CVaR Classification. NeurIPS 2021: 21860-21871 - [c78]Yujia Huang, Huan Zhang, Yuanyuan Shi, J. Zico Kolter, Anima Anandkumar:
Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds. NeurIPS 2021: 22745-22757 - [c77]Leslie Rice, Anna Bair, Huan Zhang, J. Zico Kolter:
Robustness between the worst and average case. NeurIPS 2021: 27840-27851 - [c76]Priya L. Donti, Aayushya Agarwal, Neeraj Vijay Bedmutha, Larry T. Pileggi, J. Zico Kolter:
Adversarially robust learning for security-constrained optimal power flow. NeurIPS 2021: 28677-28689 - [c75]Shiqi Wang, Huan Zhang, Kaidi Xu, Xue Lin, Suman Jana, Cho-Jui Hsieh, J. Zico Kolter:
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification. NeurIPS 2021: 29909-29921 - [i73]Devin Willmott, Anit Kumar Sahu, Fatemeh Sheikholeslami, Filipe Condessa, J. Zico Kolter:
You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries. CoRR abs/2102.00029 (2021) - [i72]Leonid Boytsov, Zico Kolter:
Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits. CoRR abs/2102.06815 (2021) - [i71]Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Sivaraman Balakrishnan, Zachary C. Lipton, Ruslan Salakhutdinov, Pradeep Ravikumar:
On Proximal Policy Optimization's Heavy-tailed Gradients. CoRR abs/2102.10264 (2021) - [i70]Jeremy Cohen, Simran Kaur, Yuanzhi Li, J. Zico Kolter