Follow
Spencer Frei
Title
Cited by
Cited by
Year
Trained Transformers Learn Linear Models In-Context
R Zhang, S Frei, PL Bartlett
Journal of Machine Learning Research 25 (49), 2024
1702024
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
S Frei, NS Chatterji, PL Bartlett
Conference on Learning Theory (COLT), 2022
942022
Agnostic Learning of a Single Neuron with Gradient Descent
S Frei, Y Cao, Q Gu
Advances in Neural Information Processing Systems (NeurIPS), 2020
692020
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data
S Frei, G Vardi, PL Bartlett, N Srebro, W Hu
International Conference on Learning Representations (ICLR), 2023
492023
Algorithm-dependent generalization bounds for overparameterized deep residual networks
S Frei, Y Cao, Q Gu
Advances in Neural Information Processing Systems (NeurIPS), 2019
382019
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization
S Frei, G Vardi, PL Bartlett, N Srebro
Conference on Learning Theory (COLT), 2023
362023
Random Feature Amplification: Feature Learning and Generalization in Neural Networks
S Frei, NS Chatterji, PL Bartlett
Journal of Machine Learning Research 24 (303), 2023
322023
Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent
S Frei, Q Gu
Advances in Neural Information Processing Systems (NeurIPS), 2021
282021
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
Z Xu, Y Wang, S Frei, G Vardi, W Hu
International Conference on Learning Representations (ICLR), 2024
262024
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
S Frei, Y Cao, Q Gu
International Conference on Machine Learning (ICML), 2021
232021
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
S Frei, G Vardi, PL Bartlett, N Srebro
Advances in Neural Information Processing Systems (NeurIPS), 2023
212023
Self-training converts weak learners to strong learners in mixture models
S Frei, D Zou, Z Chen, Q Gu
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
202022
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
S Frei, Y Cao, Q Gu
International Conference on Machine Learning (ICML), 2021
192021
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
D Zou, S Frei, Q Gu
International Conference on Machine Learning (ICML), 2021
162021
A lower bound for in range- bond percolation in two and three dimensions
S Frei, E Perkins
Electronic Journal of Probability 21, 2016
112016
Hemodynamic latency is associated with reduced intelligence across the lifespan: an fMRI DCM study of aging, cerebrovascular integrity, and cognitive ability.
AE Anderson, M Diaz‑Santos, S Frei, BH Dang, P Kaur, P Lyden, ...
Brain Structure & Function, 2020
92020
On thermal resistance in concentric residential geothermal heat exchangers
S Frei, K Lockwood, G Stewart, J Boyer, BS Tilley
Journal of Engineering Mathematics 86 (1), 103-124, 2014
52014
Benign Overfitting in Single-Head Attention
R Magen, S Shang, Z Xu, S Frei, W Hu, G Vardi
arXiv preprint arXiv:2410.07746, 2024
22024
Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
S Frei, G Vardi
arXiv preprint arXiv:2410.01774, 2024
12024
Minimum-Norm Interpolation Under Covariate Shift
N Mallinar, A Zane, S Frei, B Yu
arXiv preprint arXiv:2404.00522, 2024
12024
The system can't perform the operation now. Try again later.
Articles 1–20