Neha S. Wadia

Publication Activity (10 Years)

Years Active: 2019-2023
Publications (10 Years): 6

Top Topics

Top Venues

Publications

Neha S. Wadia, Yatin Dandi, Michael I. Jordan
A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning. CoRR (2023)
Neha S. Wadia, Daniel Duckworth, Samuel S. Schoenholz, Ethan Dyer, Jascha Sohl-Dickstein
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization. ICML (2021)
Charles G. Frye, James Simon, Neha S. Wadia, Andrew Ligeralde, Michael Robert DeWeese, Kristofer E. Bouchard
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses. Neural Comput. 33 (6) (2021)
Charles G. Frye, James Simon, Neha S. Wadia, Andrew Ligeralde, Michael Robert DeWeese, Kristofer E. Bouchard
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses. CoRR (2020)
Neha S. Wadia, Daniel Duckworth, Samuel S. Schoenholz, Ethan Dyer, Jascha Sohl-Dickstein
Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible. CoRR (2020)
Charles G. Frye, Neha S. Wadia, Michael Robert DeWeese, Kristofer E. Bouchard
Numerically Recovering the Critical Points of a Deep Linear Autoencoder. CoRR (2019)