Picture for Aaron Mishkin

Aaron Mishkin

Exploring the loss landscape of regularized neural networks via convex duality

Add code
Nov 12, 2024
Figure 1 for Exploring the loss landscape of regularized neural networks via convex duality
Figure 2 for Exploring the loss landscape of regularized neural networks via convex duality
Figure 3 for Exploring the loss landscape of regularized neural networks via convex duality
Figure 4 for Exploring the loss landscape of regularized neural networks via convex duality
Viaarxiv icon

Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation

Add code
Apr 03, 2024
Viaarxiv icon

Directional Smoothness and Gradient Methods: Convergence and Adaptivity

Add code
Mar 06, 2024
Figure 1 for Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Figure 2 for Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Figure 3 for Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Figure 4 for Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Viaarxiv icon

Level Set Teleportation: An Optimization Perspective

Add code
Mar 05, 2024
Viaarxiv icon

A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features

Add code
Mar 02, 2024
Figure 1 for A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features
Figure 2 for A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features
Figure 3 for A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features
Figure 4 for A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features
Viaarxiv icon

Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm

Add code
Jul 03, 2023
Viaarxiv icon

Optimal Sets and Solution Paths of ReLU Networks

Add code
May 31, 2023
Viaarxiv icon

Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions

Add code
Feb 05, 2022
Figure 1 for Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
Figure 2 for Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
Figure 3 for Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
Figure 4 for Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
Viaarxiv icon

To Each Optimizer a Norm, To Each Norm its Generalization

Add code
Jun 11, 2020
Figure 1 for To Each Optimizer a Norm, To Each Norm its Generalization
Figure 2 for To Each Optimizer a Norm, To Each Norm its Generalization
Figure 3 for To Each Optimizer a Norm, To Each Norm its Generalization
Figure 4 for To Each Optimizer a Norm, To Each Norm its Generalization
Viaarxiv icon

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

Add code
May 24, 2019
Figure 1 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Figure 2 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Figure 3 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Figure 4 for Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
Viaarxiv icon