Edgar Dobriban

CoRR, 2024

Watermarking Language Models with Error Correcting Codes.

[BibT_eX]

[DOI]

Patrick Chao

Hamed Hassani

CoRR, 2024

One-Shot Safety Alignment for Large Language Models via Optimal Dualization.

[BibT_eX]

[DOI]

CoRR, 2024

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

[BibT_eX]

[DOI]

Patrick Chao

Edoardo Debenedetti

Alexander Robey

Maksym Andriushchenko

CoRR, 2024

Minimax Optimal Fair Classification with Bounded Demographic Disparity.

[BibT_eX]

[DOI]

CoRR, 2024

Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing.

[BibT_eX]

[DOI]

CoRR, 2024

A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

PAC Prediction Sets Under Label Shift.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Uncertainty in Language Models: Assessment through Rank-Calibration.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023

Provable Tradeoffs in Adversarially Robust Classification.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, December, 2023

Learning Augmentation Distributions using Transformed Risk Minimization.

[BibT_eX]

[DOI]

Evangelos Chatzipantazis

Stefanos Pertigkiozoglou

Kostas Daniilidis

Trans. Mach. Learn. Res., 2023

Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queries.

[BibT_eX]

[DOI]

Matteo Sesia

Stefano Favaro

J. Mach. Learn. Res., 2023

T-Cal: An Optimal Test for the Calibration of Predictive Models.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2023

Pursuit of a discriminative representation for multiple subspaces via sequential games.

[BibT_eX]

[DOI]

J. Frankl. Inst., 2023

SymmPI: Predictive Inference for Data with Group Symmetries.

[BibT_eX]

[DOI]

Mengxin Yu

CoRR, 2023

Jailbreaking Black Box Large Language Models in Twenty Queries.

[BibT_eX]

[DOI]

CoRR, 2023

Statistical Estimation Under Distribution Shift: Wasserstein Perturbations and Minimax Theory.

[BibT_eX]

[DOI]

Patrick Chao

CoRR, 2023

Optimal Heterogeneous Collaborative Linear Regression and Contextual Bandits.

[BibT_eX]

[DOI]

CoRR, 2023

Automatically Predicting Perceived Conversation Quality in a Pediatric Sample Enriched for Autism.

[BibT_eX]

[DOI]

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Demystifying Disagreement-on-the-Line in High Dimensions.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space.

[BibT_eX]

[DOI]

Evangelos Chatzipantazis

Stefanos Pertigkiozoglou

Kostas Daniilidis

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Memory Classifiers: Two-stage Classification for Robustness in Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2022

Collaborative Learning of Distributions under Heterogeneity and Communication Constraints.

[BibT_eX]

[DOI]

CoRR, 2022

Bayes-Optimal Classifiers under Group Fairness.

[BibT_eX]

[DOI]

CoRR, 2022

Fair Bayes-Optimal Classifiers Under Predictive Parity.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

PAC Prediction Sets for Meta-Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

PAC-Wrap: Semi-Supervised PAC Anomaly Detection.

[BibT_eX]

[DOI]

Proceedings of the KDD '22: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14, 2022

Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

PAC Prediction Sets Under Covariate Shift.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates.

[BibT_eX]

[DOI]

Proceedings of the Conference on Robot Learning, 2022

iDECODe: In-Distribution Equivariance for Conformal Out-of-Distribution Detection.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

How to Reduce Dimension With PCA and Random Projections?

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2021

What Causes the Test Error? Going Beyond Bias-Variance via ANOVA.

[BibT_eX]

[DOI]

Licong Lin

J. Mach. Learn. Res., 2021

Solon: Communication-efficient Byzantine-resilient Distributed Training via Redundant Gradients.

[BibT_eX]

[DOI]

CoRR, 2021

Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?

[BibT_eX]

[DOI]

Dominic Richards

Patrick Rebeschini

CoRR, 2021

Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition.

[BibT_eX]

[DOI]

CoRR, 2021

Sparse sketches with small inversion bias.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

2020

WONDER: Weighted One-shot Distributed Ridge Regression in High Dimensions.

[BibT_eX]

[DOI]

Yue Sheng

J. Mach. Learn. Res., 2020

Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods.

[BibT_eX]

[DOI]

CoRR, 2020

Implicit Regularization and Convergence for Weight Normalization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

A Group-Theoretic Framework for Data Augmentation.

[BibT_eX]

[DOI]

Shuxiao Chen

Jane H. Lee

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

DeltaGrad: Rapid retraining of machine learning models.

[BibT_eX]

[DOI]

Yinjun Wu

Susan B. Davidson

Proceedings of the 37th International Conference on Machine Learning, 2020

One-shot Distributed Ridge Regression in High Dimensions.

[BibT_eX]

[DOI]

Yue Sheng

Proceedings of the 37th International Conference on Machine Learning, 2020

The Implicit Regularization of Stochastic Gradient Flow for Least Squares.

[BibT_eX]

[DOI]

Alnur Ali

Ryan J. Tibshirani

Proceedings of the 37th International Conference on Machine Learning, 2020

Ridge Regression: Structure, Cross-Validation, and Sketching.

[BibT_eX]

[DOI]

Sifan Liu

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Implicit Regularization of Normalization Methods.

[BibT_eX]

[DOI]

CoRR, 2019

Invariance reduces Variance: Understanding Data Augmentation in Deep Learning and Beyond.

[BibT_eX]

[DOI]

Shuxiao Chen

Jane H. Lee

CoRR, 2019

Asymptotics for Sketching in Least Squares Regression.

[BibT_eX]

[DOI]

Sifan Liu

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

A New Theory for Sketching in Linear Regression.

[BibT_eX]

[DOI]