Picture for Hailiang Liu

Hailiang Liu

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

SGEM: stochastic gradient with energy and momentum

Add code
Aug 03, 2022
Figure 1 for SGEM: stochastic gradient with energy and momentum
Figure 2 for SGEM: stochastic gradient with energy and momentum
Figure 3 for SGEM: stochastic gradient with energy and momentum
Figure 4 for SGEM: stochastic gradient with energy and momentum
Viaarxiv icon

An Adaptive Gradient Method with Energy and Momentum

Add code
Mar 23, 2022
Figure 1 for An Adaptive Gradient Method with Energy and Momentum
Figure 2 for An Adaptive Gradient Method with Energy and Momentum
Figure 3 for An Adaptive Gradient Method with Energy and Momentum
Figure 4 for An Adaptive Gradient Method with Energy and Momentum
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

AEGD: Adaptive Gradient Decent with Energy

Add code
Oct 10, 2020
Figure 1 for AEGD: Adaptive Gradient Decent with Energy
Figure 2 for AEGD: Adaptive Gradient Decent with Energy
Figure 3 for AEGD: Adaptive Gradient Decent with Energy
Figure 4 for AEGD: Adaptive Gradient Decent with Energy
Viaarxiv icon