Picture for Matilde Gargiani

Matilde Gargiani

PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation

Add code
Feb 01, 2022
Figure 1 for PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Figure 2 for PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Figure 3 for PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Figure 4 for PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Viaarxiv icon

Convergence Analysis of Homotopy-SGD for non-convex optimization

Add code
Nov 20, 2020
Figure 1 for Convergence Analysis of Homotopy-SGD for non-convex optimization
Figure 2 for Convergence Analysis of Homotopy-SGD for non-convex optimization
Figure 3 for Convergence Analysis of Homotopy-SGD for non-convex optimization
Figure 4 for Convergence Analysis of Homotopy-SGD for non-convex optimization
Viaarxiv icon

On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs

Add code
Jun 09, 2020
Figure 1 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Figure 2 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Figure 3 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Figure 4 for On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Viaarxiv icon

Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings

Add code
Oct 10, 2019
Figure 1 for Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
Figure 2 for Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
Figure 3 for Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
Figure 4 for Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
Viaarxiv icon

A Distributed Second-Order Algorithm You Can Trust

Add code
Jun 20, 2018
Figure 1 for A Distributed Second-Order Algorithm You Can Trust
Figure 2 for A Distributed Second-Order Algorithm You Can Trust
Figure 3 for A Distributed Second-Order Algorithm You Can Trust
Figure 4 for A Distributed Second-Order Algorithm You Can Trust
Viaarxiv icon