549 citations · 1.5k across the 32 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021
Spectral Tensor Train Parameterization of Deep Learning Layers
Anton Obukhov, Maxim Rakhuba, Alexander Liniger +4
We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permi…
cs.LG2020★ 2 cited
Competitive Policy Optimization
Manish Prajapat, Kamyar Azizzadenesheli, Alexander Liniger +2
A core challenge in policy optimization in competitive Markov decision processes is the design of efficient optimization methods with desirable convergence and stability properties…