Spencer Frei

Gal Vardi

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Trained Transformers Learn Linear Models In-Context.

[BibT_eX]

[DOI]

Ruiqi Zhang

Peter L. Bartlett

J. Mach. Learn. Res., 2024

Adversarial Robustness of In-Context Learning in Transformers for Linear Regression.

[BibT_eX]

[DOI]

CoRR, 2024

Benign Overfitting in Single-Head Attention.

[BibT_eX]

[DOI]

CoRR, 2024

Minimum-Norm Interpolation Under Covariate Shift.

[BibT_eX]

[DOI]

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

Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Random Feature Amplification: Feature Learning and Generalization in Neural Networks.

[BibT_eX]

[DOI]

Niladri S. Chatterji

Peter L. Bartlett

J. Mach. Learn. Res., 2023

The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning.

[BibT_eX]

[DOI]

CoRR, 2023

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data.

[BibT_eX]

[DOI]

Niladri S. Chatterji

Peter L. Bartlett

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

Self-training Converts Weak Learners to Strong Learners in Mixture Models.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Statistical Learning with Neural Networks Trained by Gradient Descent.

[BibT_eX]

[DOI]

PhD thesis, 2021

Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise.

[BibT_eX]

[DOI]

Difan Zou

Proceedings of the 38th International Conference on Machine Learning, 2021

Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Agnostic Learning of a Single Neuron with Gradient Descent.

[BibT_eX]

[DOI]

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

2019

Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks.

[BibT_eX]

[DOI]