6 citations · 10 across the 4 of their papers we have counts for
3 papers · 1 filter
Time-inhomogeneous diffusion geometry and topology
Guillaume Huguet, Alexander Tong, Bastian Rieck +5
Diffusion condensation is a dynamic process that yields a sequence of multiscale data representations that aim to encode meaningful abstractions. It has proven effective for manifo…
Exploring the Geometry and Topology of Neural Network Loss Landscapes
Stefan Horoi, Jessie Huang, Bastian Rieck +3
Recent work has established clear links between the generalization performance of trained neural networks and the geometry of their loss landscape near the local minima to which th…
Learning Safe Policies with Expert Guidance
Jessie Huang, Fa Wu, Doina Precup +1
We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existe…