← Authors

Spencer Frei

17 papers · 2019–2025 · 6 conferences · across top CS/AI conferences

Achievements

πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (21) 🧭 Keyword Pioneer πŸƒ Academic Marathon (6) 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (10) πŸ—ƒοΈ Keyword Collector (52) πŸ’Ž Century Club (17) πŸ”₯ Unstoppable (7)

Conferences

ICML (4) NIPS (4) ICLR (3) JMLR (3) COLT (2) AISTATS (1)

Top co-authors

Quanquan Gu (7) Gal Vardi (5) Yuan Cao (4) Peter Bartlett (3) Peter L. Bartlett (3) Wei Hu (2) Bin Yu (2) Nathan Srebro (2) Difan Zou (2) Ruiqi Zhang (1)

Keywords

gradient descent (5) relu network (3) stochastic gradient descent (3) adversarial robustness (2) gradient flow (2) label noise (2) generalization bound (2) benign overfitting (2) neural network (2) feature learning (2) agnostic learning (2) neural network optimization (1) adversarial training (1) covariate shift (1) robust classification (1) nonconvex optimization (1) in-context learning (1) soft margin (1) sparse representation (1) margin maximization (1)

Papers

Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context ICLR 2025
The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning JMLR 2025
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data ICLR 2024
Minimum-Norm Interpolation Under Covariate Shift ICML 2024
Trained Transformers Learn Linear Models In-Context JMLR 2024
Random Feature Amplification: Feature Learning and Generalization in Neural Networks JMLR 2023
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization COLT 2023
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data ICLR 2023
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks NIPS 2023
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data COLT 2022
Self-training Converts Weak Learners to Strong Learners in Mixture Models AISTATS 2022
Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise ICML 2021
Provable Robustness of Adversarial Training for Learning Halfspaces with Noise ICML 2021
Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent NIPS 2021
Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins ICML 2021
Agnostic Learning of a Single Neuron with Gradient Descent NIPS 2020
Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks NIPS 2019