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

2022-04-30 · 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. 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 evolutionary-based methods and outperforms them by the number of function evaluations or execution time, often by a significant margin.

📄 PDF Abstract BibTeX arXiv:2205.00293

Code (1)

andreichertkov/ttopt 공식 구현

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Global Optimization of Atomic Clusters via Physically-Constrained Tensor Train Decomposition

2026-01-26 · Konstantin Sozykin, Nikita Rybin, Andrei Chertkov, Anh-Huy Phan 외 arxiv

The global optimization of atomic clusters represents a fundamental challenge in computational chemistry and materials science due to the exponential growth of local minima with system size (i.e., the curse of dimensiona…

Quantized Radio Map Estimation Using Tensor and Deep Generative Models

2023-03-03 · Subash Timilsina, Sagar Shrestha, Xiao Fu

Spectrum cartography (SC), also known as radio map estimation (RME), aims at crafting multi-domain (e.g., frequency and space) radio power propagation maps from limited sensor measurements. While early methods often lack…

Spectrum Cartography Tensor Decomposition

Tensor Recovery from Noisy and Multi-Level Quantized Measurements

2019-12-05 · Ren Wang, Meng Wang, JinJun Xiong

Higher-order tensors can represent scores in a rating system, frames in a video, and images of the same subject. In practice, the measurements are often highly quantized due to the sampling strategies or the quality of d…

Quantization

Are Quantum Computers Practical Yet? A Case for Feature Selection in Recommender Systems using Tensor Networks

2022-05-09 · Artyom Nikitin, Andrei Chertkov, Rafael Ballester-Ripoll, Ivan Oseledets 외

Collaborative filtering models generally perform better than content-based filtering models and do not require careful feature engineering. However, in the cold-start scenario collaborative information may be scarce or e…

Collaborative Filtering Feature Engineering feature selection Recommendation Systems+1

Quantized Fourier and Polynomial Features for more Expressive Tensor Network Models

2023-09-11 · Frederiek Wesel, Kim Batselier

In the context of kernel machines, polynomial and Fourier features are commonly used to provide a nonlinear extension to linear models by mapping the data to a higher-dimensional space. Unless one considers the dual form…