Timezone: »

 
Poster
TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning
Konstantin Sozykin · Andrei Chertkov · Roman Schutski · Anh-Huy Phan · Andrzej S CICHOCKI · Ivan Oseledets

@

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 demonstrate the applicability of the new Tensor Train Optimizer (TTOpt) method for various tasks, ranging from minimization of multidimensional functions to reinforcement learning.Our algorithm compares favorably to popular gradient-free methods and outperforms them by the number of function evaluations or execution time, often by a significant margin.

Keywords: Optimization · Reinforcement Learning · Cross approximation · Tensor Train · Maximum Volume · Quantized networks · Black-box
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Konstantin Sozykin (Skolkovo institute of science and technology)
Andrei Chertkov (Skolkovo Institute of Science and Technology)
Roman Schutski (Skoltech)
Anh-Huy Phan (​Skolkovo Institute of Science and Technology)
Andrzej S CICHOCKI (RIKEB Brain Science Institute)
Ivan Oseledets (Skolkovo Institute of Science and Technology)

More from the Same Authors