Micah Goldblum

发表

Encoding Robustness to Image Style via Adversarial Feature Perturbations

T. Goldstein, Zuxuan Wu, Manli Shu, 2020, NeurIPS.

Stochastic Training is Not Necessary for Generalization

Phillip E. Pope, T. Goldstein, Michael Moeller, 2021, ICLR.

Datasets for Studying Generalization from Easy to Hard Examples

Furong Huang, T. Goldstein, Avi Schwarzschild, 2021, ArXiv.

Bayesian Model Selection, the Marginal Likelihood, and Generalization

Gregory W. Benton, A. G. Wilson, Pavel Izmailov, 2022, ICML.

Identification of Attack-Specific Signatures in Adversarial Examples pdf

Rama Chellappa, Hossein Souri, Chun Pong Lau, 2021, ArXiv.

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

Yann LeCun, Sanyam Kapoor, Ravid Shwartz-Ziv, 2022, NeurIPS.

The Lie Derivative for Measuring Learned Equivariance

Marc Finzi, Nate Gruver, Micah Goldblum, 2022, ICLR.

On the Importance of Architectures and Hyperparameters for Fairness in Face Recognition

John P. Dickerson, F. Hutter, Colin White, 2022, ArXiv.

PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization

Sanyam Kapoor, Marc Finzi, Micah Goldblum, 2022, NeurIPS.

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

T. Goldstein, Liam Fowl, W. Czaja, 2021, ArXiv.

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

Duncan C. McElfresh, Ganesh Ramakrishnan, Colin White, 2023, ArXiv.

Bayesian Model Selection, the Marginal Likelihood, and Generalization

Gregory W. Benton, Pavel Izmailov, Micah Goldblum, 2022, ICML.

Towards Transferable Adversarial Attacks on Vision Transformers pdf

Tom Goldstein, Yu-Gang Jiang, Zuxuan Wu, 2021, AAAI.

Active Learning at the ImageNet Scale pdf

Wojciech Czaja, Tom Goldstein, Hong-Min Chu, 2021, ArXiv.

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Marc Finzi, Micah Goldblum, A. Wilson, 2023, ArXiv.

Comparing Human and Machine Bias in Face Recognition pdf

Tom Goldstein, John P. Dickerson, Valeriia Cherepanova, 2021, ArXiv.

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

Duncan C. McElfresh, Ganesh Ramakrishnan, Colin White, 2023, ArXiv.

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

Duncan C. McElfresh, Ganesh Ramakrishnan, Colin White, 2023, NeurIPS.

Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers

P. Kirichenko, Micah Goldblum, A. Wilson, 2022, NeurIPS.

Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

John P. Dickerson, F. Hutter, Micah Goldblum, 2022, 2210.09943.

TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks

R. Schirrmeister, Colin White, Micah Goldblum, 2024, ArXiv.

Simplifying Neural Network Training Under Class Imbalance

Ravid Shwartz-Ziv, Micah Goldblum, C. B. Bruss, 2023, NeurIPS.

Calibration-Tuning: Teaching Large Language Models to Know What They Don’t Know

Nate Gruver, Micah Goldblum, Manley Roberts, 2024, UNCERTAINLP.

Large Language Models Must Be Taught to Know What They Don't Know

Katherine M. Collins, Sanyam Kapoor, Nate Gruver, 2024, ArXiv.

Adaptive Rentention & Correction for Continual Learning

Zuxuan Wu, Micah Goldblum, Yu-Gang Jiang, 2024, ArXiv.

Non-Vacuous Generalization Bounds for Large Language Models

Tim G. J. Rudner, Marc Finzi, Micah Goldblum, 2023, ArXiv.

Compute Better Spent: Replacing Dense Layers with Structured Matrices

Marc Finzi, Micah Goldblum, Andres Potapczynski, 2024, ICML.