 High Dimensional Binary Classification under Label Shift: Phase
Transition and RegularizationSampling Theory, Signal Processing, and Data Analysis (SampTA), 2022 |
 Generalization for multiclass classification with overparameterized
linear modelsNeural Information Processing Systems (NeurIPS), 2022 |
 Bias-variance decomposition of overparameterized regression with random
linear featuresPhysical Review E (Phys. Rev. E), 2022 |
 Fine-Tuning can Distort Pretrained Features and Underperform
Out-of-DistributionInternational Conference on Learning Representations (ICLR), 2022 |
 Memorizing without overfitting: Bias, variance, and interpolation in
over-parameterized modelsPhysical Review Research (PRResearch), 2020 |
 |
 Optimal Regularization Can Mitigate Double DescentInternational Conference on Learning Representations (ICLR), 2020 |
 Deep Double Descent: Where Bigger Models and More Data HurtInternational Conference on Learning Representations (ICLR), 2019 |
