Part of Advances in Neural Information Processing Systems 35 (NeurIPS 2022) Main Conference Track
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.