Posts
-
Reflections on CB9, Part 4: Opinions
-
Reflections on CB9, Part 3: Lessons
-
Reflections on CB9, Part 2: Resources
-
Reflections on CB9, Part 1: Introduction
-
What does the 'R-norm' reveal about efficient neural network approximation? (COLT 2023 paper with Navid and Daniel)
-
How hard is it to learn an intersection of halfspaces? (COLT 2022 paper with Rocco, Daniel, and Manolis)
-
Books of 2021
-
How do SVMs and least-squares regression behave in high-dimensional settings? (NeurIPS 2021 paper with Navid and Daniel)
-
My candidacy exam is done!
-
[OPML#10] MNSBHS20: Classification vs regression in overparameterized regimes: Does the loss function matter?
-
[OPML#9] CL20: Finite-sample analysis of interpolating linear classifiers in the overparameterized regime
-
[OPML#8] FS97 & BFLS98: Benign overfitting in boosting
-
[OPML#7] BLN20 & BS21: Smoothness and robustness of neural net interpolators
-
[OPML#6] XH19: On the number of variables to use in principal component regression
-
How many neurons are needed to approximate smooth functions? A summary of our COLT 2021 paper
-
[OPML#5] BL20: Failures of model-dependent generalization bounds for least-norm interpolation
-
[OPML#4] HMRT19: Surprises in high-dimensional ridgeless least squares interpolation
-
Orthonormal function bases: what they are and why we care
-
[OPML#3] MVSS19: Harmless interpolation of noisy data in regression
-
[OPML#2] BLLT19: Benign overfitting in linear regression
-
[OPML#1] BHX19: Two models of double descent for weak features
-
[OPML#0] A series of posts on over-parameterized machine learning models
subscribe via RSS