2020-08
2020-06
An operator view of policy gradient methods.
To Each Optimizer a Norm, To Each Norm its Generalization.
2020-02
The Geometry of Sign Gradient Descent
2020-01
An operator view of policy gradient methods
On the interplay between noise and curvature and its effect on optimization and generalization.
2019-12
A Geometric Perspective on Optimal Representations for Reinforcement Learning
Reducing the variance in online optimization by transporting past gradients
2019-06
On the interplay between noise and curvature and its effect on optimization and generalization
Information matrices and generalization
Understanding the Impact of Entropy on Policy Optimization
The Value Function Polytope in Reinforcement Learning
2019-04
Distributional reinforcement learning with linear function approximation
AISTATS 2019
(2019-04-11)
proceedings.mlr.pressPDF[Also on arXiv preprint arXiv:1902.03149 (2019-02-08)]2019-03
Improving NILM by Combining Sensor Data and Linear Programming
2019-02
Anytime Tail Averaging.
Negative eigenvalues of the Hessian in deep neural networks.
2019-01
The Value Function Polytope in Reinforcement Learning
A Geometric Perspective on Optimal Representations for Reinforcement Learning
2018-11
Understanding the impact of entropy in policy learning
Publications collected and formatted using Paperoni