Spencer Frei

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 28

Top Topics

Agnostic Learning

Trained Neural Networks

Top Venues

Publications

Neil Mallinar, Austin Zane, Spencer Frei, Bin Yu
Minimum-Norm Interpolation Under Covariate Shift. CoRR (2024)
Zhiwei Xu, Yutong Wang, Spencer Frei, Gal Vardi, Wei Hu
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data. ICLR (2024)
Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro, Wei Hu
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data. ICLR (2023)
Zhiwei Xu, Yutong Wang, Spencer Frei, Gal Vardi, Wei Hu
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data. CoRR (2023)
Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks. CoRR (2023)
Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization. COLT (2023)
Spencer Frei, Gal Vardi, Peter L. Bartlett, Nati Srebro
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks. NeurIPS (2023)
Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization. CoRR (2023)
Ruiqi Zhang, Spencer Frei, Peter L. Bartlett
Trained Transformers Learn Linear Models In-Context. CoRR (2023)
Nikhil Ghosh, Spencer Frei, Wooseok Ha, Bin Yu
The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning. CoRR (2023)
Spencer Frei, Gal Vardi, Peter L. Bartlett, Nathan Srebro, Wei Hu
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data. CoRR (2022)
Spencer Frei, Difan Zou, Zixiang Chen, Quanquan Gu
Self-training Converts Weak Learners to Strong Learners in Mixture Models. AISTATS (2022)
Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data. COLT (2022)
Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data. CoRR (2022)
Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett
Random Feature Amplification: Feature Learning and Generalization in Neural Networks. CoRR (2022)
Spencer Frei, Quanquan Gu
Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent. NeurIPS (2021)
Spencer Frei, Yuan Cao, Quanquan Gu
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins. ICML (2021)
Spencer Frei, Difan Zou, Zixiang Chen, Quanquan Gu
Self-training Converts Weak Learners to Strong Learners in Mixture Models. CoRR (2021)
Difan Zou, Spencer Frei, Quanquan Gu
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise. ICML (2021)
Spencer Frei, Yuan Cao, Quanquan Gu
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise. ICML (2021)
Spencer Frei, Yuan Cao, Quanquan Gu
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise. CoRR (2021)
Spencer Frei, Quanquan Gu
Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent. CoRR (2021)
Difan Zou, Spencer Frei, Quanquan Gu
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise. CoRR (2021)
Spencer Frei, Yuan Cao, Quanquan Gu
Agnostic Learning of a Single Neuron with Gradient Descent. NeurIPS (2020)
Spencer Frei, Yuan Cao, Quanquan Gu
Agnostic Learning of a Single Neuron with Gradient Descent. CoRR (2020)
Spencer Frei, Yuan Cao, Quanquan Gu
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins. CoRR (2020)
Spencer Frei, Yuan Cao, Quanquan Gu
Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks. NeurIPS (2019)
Spencer Frei, Yuan Cao, Quanquan Gu
Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks. CoRR (2019)