26 citations · 64 across the 8 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 1 cited
Few-Shot Learning by Dimensionality Reduction in Gradient Space
Martin Gauch, Maximilian Beck, Thomas Adler +10
We introduce SubGD, a novel few-shot learning method which is based on the recent finding that stochastic gradient descent updates tend to live in a low-dimensional parameter subsp…
cs.LG2022★ 4 cited
History Compression via Language Models in Reinforcement Learning
Fabian Paischer, Thomas Adler, Vihang Patil +5
In a partially observable Markov decision process (POMDP), an agent typically uses a representation of the past to approximate the underlying MDP. We propose to utilize a frozen Pr…