Alert button
Picture for Neha S. Wadia

Neha S. Wadia

Alert button

A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning

Sep 09, 2023
Neha S. Wadia, Yatin Dandi, Michael I. Jordan

Figure 1 for A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning
Figure 2 for A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning
Figure 3 for A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning
Figure 4 for A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning
Viaarxiv icon

Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible

Aug 25, 2020
Neha S. Wadia, Daniel Duckworth, Samuel S. Schoenholz, Ethan Dyer, Jascha Sohl-Dickstein

Figure 1 for Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible
Figure 2 for Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible
Figure 3 for Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible
Figure 4 for Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible
Viaarxiv icon

Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses

Mar 23, 2020
Charles G. Frye, James Simon, Neha S. Wadia, Andrew Ligeralde, Michael R. DeWeese, Kristofer E. Bouchard

Figure 1 for Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses
Figure 2 for Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses
Figure 3 for Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses
Figure 4 for Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses
Viaarxiv icon

Numerically Recovering the Critical Points of a Deep Linear Autoencoder

Jan 29, 2019
Charles G. Frye, Neha S. Wadia, Michael R. DeWeese, Kristofer E. Bouchard

Figure 1 for Numerically Recovering the Critical Points of a Deep Linear Autoencoder
Figure 2 for Numerically Recovering the Critical Points of a Deep Linear Autoencoder
Figure 3 for Numerically Recovering the Critical Points of a Deep Linear Autoencoder
Figure 4 for Numerically Recovering the Critical Points of a Deep Linear Autoencoder
Viaarxiv icon