research
∙
02/01/2022
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Despite their success, policy gradient methods suffer from high variance...
share
research
∙
11/20/2020
Convergence Analysis of Homotopy-SGD for non-convex optimization
First-order stochastic methods for solving large-scale non-convex optimi...
research
∙
06/03/2020
On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs
Following early work on Hessian-free methods for deep learning, we study...
research
∙
10/10/2019
Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings
We propose probabilistic models that can extrapolate learning curves of ...
research
∙
06/20/2018