Maxim Rakhuba

National Research University Higher School of Economics — Russia

Mathematics · Physical Sciences

7h-index186citations61works0.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Tensor decomposition and applications(37), Matrix Theory and Algorithms(20), Model Reduction and Neural Networks(10), Sparse and Compressive Sensing Techniques(9), Advanced Numerical Methods in Computational Mathematics(7)

Publications61 total

Optimization on the extended tensor-train manifold with shared factors
Computational and Applied Mathematics·2026
Low-rank matrix and tensor approximations for compression of machine-learning interatomic potentials
The Journal of Chemical Physics·2025· 1 citedOpen Access
Ultra Fast Warm Start Solution for Graph Recommendations
2025
Dimension-free Bounds for Covariance Estimation with Tensor-Train Structure
ArXiv.org·2025Open Access
Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
2025
Ultra Fast Warm Start Solution for Graph Recommendations
arXiv (Cornell University)·2025Open Access
Optimization on the Extended Tensor-Train Manifold with Shared Factors
arXiv (Cornell University)·2025Open Access
Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations
arXiv (Cornell University)·2025Open Access
LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
arXiv (Cornell University)·2025· 1 citedOpen Access
COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation
arXiv (Cornell University)·2025Open Access
Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers
arXiv (Cornell University)·2025Open Access
On the Upper Bounds for the Matrix Spectral Norm
arXiv (Cornell University)·2025Open Access
Accelerating Newton-Schulz Iteration for Orthogonalization via Chebyshev-type Polynomials
ArXiv.org·2025Open Access
ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations
arXiv (Cornell University)·2025Open Access
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
arXiv (Cornell University)·2025Open Access
Supplementary material to the manuscriptSI : Low-rank matrix and tensor approximations for compression of machine-learning interatomic potentials
AIP Publishing·2025Open Access
ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations
2025
Low-rank matrix and tensor approximations for compression of machine-learning interatomic potentials
AIP Publishing·2025Open Access
Supplementary material to the manuscriptSI : Low-rank matrix and tensor approximations for compression of machine-learning interatomic potentials
AIP Publishing·2025Open Access
Low-rank matrix and tensor approximations for compression of machine-learning interatomic potentials
AIP Publishing·2025Open Access
page 1 of 4Next →

Frequent Co-authors

Ivan Oseledets(20), Carlo Marcati(6), Mikhail Gorbunov(5), André Uschmajew(4), Ekaterina Grishina(4), V. S. Yusupov(4), Evgeny Frolov(4), Christoph Schwab(3), Anton Obukhov(3), Alexander Novikov(3), Johan E. M. Ulander(3), Alexander Molozhavenko(3), Valentin Khrulkov(3), Vladimir Kazeev(2), Stamatios Georgoulis(2), Dengxin Dai(2), Luc Van Gool(2), Lev I. Vysotsky(2), Andrei Chertkov(2), Mikhail Usvyatsov(2)