Search Results for author: Roman Schutski

Found 4 papers, 2 papers with code

TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning

1 code implementation30 Apr 2022 Konstantin Sozykin, Andrei Chertkov, Roman Schutski, Anh-Huy Phan, Andrzej 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.

reinforcement-learning Reinforcement Learning (RL)

Graph Convolutional Policy for Solving Tree Decomposition via Reinforcement Learning Heuristics

no code implementations18 Oct 2019 Taras Khakhulin, Roman Schutski, Ivan Oseledets

We show that the agent builton GCN and trained on a single graph using an Actor-Critic method can efficiently generalize to real-world TD problem instances.

reinforcement-learning Reinforcement Learning (RL) +1

Tensor-Structured Coupled Cluster Theory

1 code implementation8 Aug 2017 Roman Schutski, Jinmo Zhao, Thomas M. Henderson, Gustavo E. Scuseria

We derive and implement a new way of solving coupled cluster equations with lower computational scaling.

Chemical Physics Strongly Correlated Electrons

Cannot find the paper you are looking for? You can Submit a new open access paper.