Picture for Tianxiang Gao

Tianxiang Gao

Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models

Add code
Oct 16, 2023
Figure 1 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Figure 2 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Figure 3 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Figure 4 for Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
Viaarxiv icon

On the optimization and generalization of overparameterized implicit neural networks

Add code
Sep 30, 2022
Figure 1 for On the optimization and generalization of overparameterized implicit neural networks
Viaarxiv icon

Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths

Add code
May 16, 2022
Figure 1 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Figure 2 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Figure 3 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Figure 4 for Gradient Descent Optimizes Infinite-Depth ReLU Implicit Networks with Linear Widths
Viaarxiv icon

A global convergence theory for deep ReLU implicit networks via over-parameterization

Add code
Oct 11, 2021
Figure 1 for A global convergence theory for deep ReLU implicit networks via over-parameterization
Viaarxiv icon

Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems

Add code
May 04, 2021
Figure 1 for Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems
Figure 2 for Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems
Figure 3 for Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems
Figure 4 for Alternate Model Growth and Pruning for Efficient Training of Recommendation Systems
Viaarxiv icon

Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization

Add code
Jan 15, 2020
Figure 1 for Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
Figure 2 for Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
Figure 3 for Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
Figure 4 for Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
Viaarxiv icon

Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems

Add code
Dec 16, 2019
Figure 1 for Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems
Figure 2 for Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems
Figure 3 for Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems
Figure 4 for Leveraging Two Reference Functions in Block Bregman Proximal Gradient Descent for Non-convex and Non-Lipschitz Problems
Viaarxiv icon

A Forest from the Trees: Generation through Neighborhoods

Add code
Feb 04, 2019
Figure 1 for A Forest from the Trees: Generation through Neighborhoods
Figure 2 for A Forest from the Trees: Generation through Neighborhoods
Figure 3 for A Forest from the Trees: Generation through Neighborhoods
Figure 4 for A Forest from the Trees: Generation through Neighborhoods
Viaarxiv icon

DID: Distributed Incremental Block Coordinate Descent for Nonnegative Matrix Factorization

Add code
Feb 25, 2018
Figure 1 for DID: Distributed Incremental Block Coordinate Descent for Nonnegative Matrix Factorization
Figure 2 for DID: Distributed Incremental Block Coordinate Descent for Nonnegative Matrix Factorization
Figure 3 for DID: Distributed Incremental Block Coordinate Descent for Nonnegative Matrix Factorization
Viaarxiv icon

Degrees of Freedom in Deep Neural Networks

Add code
Jun 03, 2016
Figure 1 for Degrees of Freedom in Deep Neural Networks
Figure 2 for Degrees of Freedom in Deep Neural Networks
Figure 3 for Degrees of Freedom in Deep Neural Networks
Figure 4 for Degrees of Freedom in Deep Neural Networks
Viaarxiv icon