1.4k citations · 5.9k across the 68 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 9 cited
TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning
Konstantin Sozykin, Andrei Chertkov, Roman Schutski +3
We present a novel procedure for optimization based on the combination of efficient quantized tensor train representation and a generalized maximum matrix volume principle. We demo…
cs.LG2022
How to Train Unstable Looped Tensor Network
Anh-Huy Phan, Konstantin Sobolev, Dmitry Ermilov +4
A rising problem in the compression of Deep Neural Networks is how to reduce the number of parameters in convolutional kernels and the complexity of these layers by low-rank tensor…