Posts

• Jul 12, 2023

  What does the 'R-norm' reveal about efficient neural network approximation? (COLT 2023 paper with Navid and Daniel)

• Jul 30, 2022

  How hard is it to learn an intersection of halfspaces? (COLT 2022 paper with Rocco, Daniel, and Manolis)

• Jan 3, 2022

  Books of 2021

• Dec 7, 2021

  How do SVMs and least-squares regression behave in high-dimensional settings? (NeurIPS 2021 paper with Navid and Daniel)

• Nov 17, 2021

  My candidacy exam is done!

• Nov 4, 2021

  [OPML#10] MNSBHS20: Classification vs regression in overparameterized regimes: Does the loss function matter?

• Oct 28, 2021

  [OPML#9] CL20: Finite-sample analysis of interpolating linear classifiers in the overparameterized regime

• Oct 20, 2021

  [OPML#8] FS97 & BFLS98: Benign overfitting in boosting

• Sep 22, 2021

  [OPML#7] BLN20 & BS21: Smoothness and robustness of neural net interpolators

• Sep 11, 2021

  [OPML#6] XH19: On the number of variables to use in principal component regression

• Aug 15, 2021

  How many neurons are needed to approximate smooth functions? A summary of our COLT 2021 paper

• Jul 30, 2021

  [OPML#5] BL20: Failures of model-dependent generalization bounds for least-norm interpolation

• Jul 23, 2021

  [OPML#4] HMRT19: Surprises in high-dimensional ridgeless least squares interpolation

• Jul 16, 2021

  Orthonormal function bases: what they are and why we care

• Jul 16, 2021

  [OPML#3] MVSS19: Harmless interpolation of noisy data in regression

• Jul 11, 2021

  [OPML#2] BLLT19: Benign overfitting in linear regression

• Jul 5, 2021

  [OPML#1] BHX19: Two models of double descent for weak features

• Jul 4, 2021

  [OPML#0] A series of posts on over-parameterized machine learning models

subscribe via RSS