Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tom Goldstein

Are Commercial Face Detection Models as Biased as Academic Models?


Jan 25, 2022
Samuel Dooley, George Z. Wei, Tom Goldstein, John P. Dickerson


  Access Paper or Ask Questions

Execute Order 66: Targeted Data Poisoning for Reinforcement Learning


Jan 03, 2022
Harrison Foley, Liam Fowl, Tom Goldstein, Gavin Taylor

* Workshop on Safe and Robust Control of Uncertain Systems at the 35th Conference on Neural Information Processing Systems 

  Access Paper or Ask Questions

Hybrid Jammer Mitigation for All-Digital mmWave Massive MU-MIMO


Nov 25, 2021
Gian Marti, Oscar Castañeda, Sven Jacobsson, Giuseppe Durisi, Tom Goldstein, Christoph Studer

* Appeared at the Asilomar Conference on Signals, Systems, and Computers 2021 

  Access Paper or Ask Questions

Active Learning at the ImageNet Scale


Nov 25, 2021
Zeyad Ali Sami Emam, Hong-Min Chu, Ping-Yeh Chiang, Wojciech Czaja, Richard Leapman, Micah Goldblum, Tom Goldstein


  Access Paper or Ask Questions

Joint Channel Estimation and Data Detection in Cell-Free Massive MU-MIMO Systems


Oct 29, 2021
Haochuan Song, Tom Goldstein, Xiaohu You, Chuan Zhang, Olav Tirkkonen, Christoph Studer

* To appear in the IEEE Transactions on Wireless Communications 

  Access Paper or Ask Questions

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization


Oct 27, 2021
Mucong Ding, Kezhi Kong, Jingling Li, Chen Zhu, John P Dickerson, Furong Huang, Tom Goldstein

* NeurIPS 2021 

  Access Paper or Ask Questions

A Frequency Perspective of Adversarial Robustness


Oct 26, 2021
Shishira R Maiya, Max Ehrlich, Vatsal Agarwal, Ser-Nam Lim, Tom Goldstein, Abhinav Shrivastava


  Access Paper or Ask Questions

Convergent Boosted Smoothing for Modeling Graph Data with Tabular Node Features


Oct 26, 2021
Jiuhai Chen, Jonas Mueller, Vassilis N. Ioannidis, Soji Adeshina, Yangkun Wang, Tom Goldstein, David Wipf


  Access Paper or Ask Questions

Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models


Oct 25, 2021
Liam Fowl, Jonas Geiping, Wojtek Czaja, Micah Goldblum, Tom Goldstein


  Access Paper or Ask Questions

Comparing Human and Machine Bias in Face Recognition


Oct 25, 2021
Samuel Dooley, Ryan Downing, George Wei, Nathan Shankar, Bradon Thymes, Gudrun Thorkelsdottir, Tiye Kurtz-Miott, Rachel Mattson, Olufemi Obiwumi, Valeriia Cherepanova, Micah Goldblum, John P Dickerson, Tom Goldstein


  Access Paper or Ask Questions

Stochastic Training is Not Necessary for Generalization


Sep 29, 2021
Jonas Geiping, Micah Goldblum, Phillip E. Pope, Michael Moeller, Tom Goldstein

* 20 pages, 4 figures. Code published at github.com/JonasGeiping/fullbatchtraining 

  Access Paper or Ask Questions

Towards Transferable Adversarial Attacks on Vision Transformers


Sep 18, 2021
Zhipeng Wei, Jingjing Chen, Micah Goldblum, Zuxuan Wu, Tom Goldstein, Yu-Gang Jiang


  Access Paper or Ask Questions

Robustness Disparities in Commercial Face Detection


Aug 27, 2021
Samuel Dooley, Tom Goldstein, John P. Dickerson


  Access Paper or Ask Questions

Datasets for Studying Generalization from Easy to Hard Examples


Aug 13, 2021
Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Arpit Bansal, Zeyad Emam, Furong Huang, Micah Goldblum, Tom Goldstein


  Access Paper or Ask Questions

Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability


Aug 03, 2021
Roman Levin, Manli Shu, Eitan Borgnia, Furong Huang, Micah Goldblum, Tom Goldstein


  Access Paper or Ask Questions

Long-Short Transformer: Efficient Transformers for Language and Vision


Jul 27, 2021
Chen Zhu, Wei Ping, Chaowei Xiao, Mohammad Shoeybi, Tom Goldstein, Anima Anandkumar, Bryan Catanzaro


  Access Paper or Ask Questions

Adversarial Examples Make Strong Poisons


Jun 21, 2021
Liam Fowl, Micah Goldblum, Ping-yeh Chiang, Jonas Geiping, Wojtek Czaja, Tom Goldstein


  Access Paper or Ask Questions

MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data


Jun 17, 2021
Arpit Bansal, Micah Goldblum, Valeriia Cherepanova, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein


  Access Paper or Ask Questions

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch


Jun 16, 2021
Hossein Souri, Micah Goldblum, Liam Fowl, Rama Chellappa, Tom Goldstein


  Access Paper or Ask Questions

Learning Revenue-Maximizing Auctions With Differentiable Matching


Jun 15, 2021
Michael J. Curry, Uro Lyi, Tom Goldstein, John Dickerson


  Access Paper or Ask Questions

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks


Jun 08, 2021
Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, Tom Goldstein


  Access Paper or Ask Questions

SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training


Jun 02, 2021
Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C. Bayan Bruss, Tom Goldstein


  Access Paper or Ask Questions

The Intrinsic Dimension of Images and Its Impact on Learning


Apr 18, 2021
Phillip Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein

* To appear at ICLR 2021 (spotlight), 17 pages with appendix, 15 figures 

  Access Paper or Ask Questions

THAT: Two Head Adversarial Training for Improving Robustness at Scale


Mar 25, 2021
Zuxuan Wu, Tom Goldstein, Larry S. Davis, Ser-Nam Lim


  Access Paper or Ask Questions

Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracy


Mar 21, 2021
Chen Chen, Kezhi Kong, Peihong Yu, Juan Luque, Tom Goldstein, Furong Huang


  Access Paper or Ask Questions

Thinking Deeply with Recurrence: Generalizing from Easy to Hard Sequential Reasoning Problems


Mar 17, 2021
Avi Schwarzschild, Arjun Gupta, Micah Goldblum, Tom Goldstein


  Access Paper or Ask Questions

Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving


Mar 15, 2021
Shivam Akhauri, Laura Zheng, Tom Goldstein, Ming Lin

* 6 pages, 3 figures, 8 tables 

  Access Paper or Ask Questions