Spencer Frei

发表

Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins

Quanquan Gu, Spencer Frei, Yuan Cao, 2020, ICML.

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

Yuan Cao, Quanquan Gu, Spencer Frei, 2021, ICML.

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

Quanquan Gu, Spencer Frei, Quanquan Gu, 2021, NeurIPS.

Hemodynamic latency is associated with reduced intelligence across the lifespan: an fMRI DCM study of aging, cerebrovascular integrity, and cognitive ability

Karl J. Friston, Ariana E. Anderson, P. Douglas, 2020, Brain Structure and Function.

Hemodynamic latency is associated with reduced intelligence: an fMRI DCM study of aging, cerebrovascular integrity, and cognitive ability

Karl J. Friston, Ariana E. Anderson, P. Douglas, 2020 .

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

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, COLT.

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

Quanquan Gu, Spencer Frei, 2021, NeurIPS.

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

P. Bartlett, Nathan Srebro, Wei Hu, 2022, ICLR.

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, ArXiv.

Agnostic Learning of a Single Neuron with Gradient Descent

Quanquan Gu, Yuan Cao, Spencer Frei, 2020, NeurIPS.

A lower bound for $p_c$ in range-$R$ bond percolation in two and three dimensions

Spencer Frei, E. Perkins, 2016, 1603.04130.

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

P. Bartlett, Nathan Srebro, Gal Vardi, 2023, COLT.

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

P. Bartlett, Nathan Srebro, Gal Vardi, 2023, ArXiv.

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

Quanquan Gu, Yuanbin Cao, Spencer Frei, 2021, ICML.

Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks

Yuan Cao, Quanquan Gu, Spencer Frei, 2019, NeurIPS.

Trained Transformers Learn Linear Models In-Context

P. Bartlett, Spencer Frei, Ruiqi Zhang, 2023, ArXiv.

Weak convergence methods for nonlinear partial differential equations

Spencer Frei, Brian Seguin, Benjamin Landon, 2012 .

Trained Transformers Learn Linear Models In-Context

P. Bartlett, Spencer Frei, Ruiqi Zhang, 2023, ArXiv.

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

Ting Yu, Wooseok Ha, Spencer Frei, 2023, ArXiv.

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

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, COLT.

Trained Transformers Learn Linear Models In-Context

P. Bartlett, Spencer Frei, Ruiqi Zhang, 2023, ArXiv.

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

Niladri S. Chatterji, P. Bartlett, Spencer Frei, 2022, ArXiv.

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

Quanquan Gu, Spencer Frei, Difan Zou, 2021, AISTATS.