Maksim Rakhuba

According to our database, Maksim Rakhuba authored at least 33 papers between 2015 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Ultra Fast Warm Start Solution for Graph Recommendations.

Viacheslav Yusupov, Maxim V. Rakhuba, Evgeny Frolov

CoRR, September, 2025

Optimization on the Extended Tensor-Train Manifold with Shared Factors.

Alexander Molozhavenko, Maxim V. Rakhuba

CoRR, August, 2025

Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation.

Askar Tsyganov, Evgeny Frolov, Sergey Samsonov, Maxim V. Rakhuba

CoRR, August, 2025

RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization.

Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko, Denis Bobkov, Vera Soboleva, Aibek Alanov, Maxim V. Rakhuba

CoRR, July, 2025

Pay Attention to Attention Distribution: A New Local Lipschitz Bound for Transformers.

Nikolay Yudin, Alexander Gaponov, Sergei Kudriashov, Maxim V. Rakhuba

CoRR, July, 2025

On the Upper Bounds for the Matrix Spectral Norm.

Alexey Naumov, Maxim V. Rakhuba, Denis Ryapolov, Sergey Samsonov

CoRR, June, 2025

Accelerating Newton-Schulz Iteration for Orthogonalization via Chebyshev-type Polynomials.

Ekaterina Grishina, Matvey Smirnov, Maxim V. Rakhuba

CoRR, June, 2025

Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations.

Viacheslav Yusupov, Maxim V. Rakhuba, Evgeny Frolov

Proceedings of the Nineteenth ACM Conference on Recommender Systems, 2025

Knowledge Graph Completion with Mixed Geometry Tensor Factorization.

Viacheslav Yusupov, Maxim V. Rakhuba, Evgeny Frolov

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations.

Ekaterina Grishina, Mikhail Gorbunov, Maxim V. Rakhuba

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Group and Shuffle: Efficient Structured Orthogonal Parametrization.

Mikhail Gorbunov, Nikolay Yudin, Vera Soboleva, Aibek Alanov, Alexey Naumov, Maxim V. Rakhuba

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers.

Ekaterina Grishina, Mikhail Gorbunov, Maxim V. Rakhuba

Proceedings of the Computer Vision - ECCV 2024, 2024

Dimension-free Structured Covariance Estimation.

Nikita Puchkin, Maxim V. Rakhuba

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach.

Ivan Peshekhonov, Aleksey Arzhantsev, Maxim V. Rakhuba

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Tensor rank bounds and explicit QTT representations for the inverses of circulant matrices.

Lev I. Vysotsky, Maxim V. Rakhuba

Numer. Linear Algebra Appl., May, 2023

Local convergence of alternating low-rank optimization methods with overrelaxation.

Ivan V. Oseledets, Maxim V. Rakhuba, André Uschmajew

Numer. Linear Algebra Appl., May, 2023

2022

Quantized Tensor FEM for Multiscale Problems: Diffusion Problems in Two and Three Dimensions.

Vladimir A. Kazeev, Ivan V. Oseledets, Maxim V. Rakhuba, Christoph Schwab

Multiscale Model. Simul., September, 2022

Automatic Differentiation for Riemannian Optimization on Low-Rank Matrix and Tensor-Train Manifolds.

Alexander Novikov, Maxim V. Rakhuba, Ivan V. Oseledets

SIAM J. Sci. Comput., 2022

Tensor rank bounds for point singularities in ℝ³.

Carlo Marcati, Maksim Rakhuba, Christoph Schwab

Adv. Comput. Math., 2022

Towards Practical Control of Singular Values of Convolutional Layers.

Alexandra Senderovich, Ekaterina Bulatova, Anton Obukhov, Maxim V. Rakhuba

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Robust Alternating Direction Implicit Solver in Quantized Tensor Formats for a Three-Dimensional Elliptic PDE.

Maxim V. Rakhuba

SIAM J. Sci. Comput., 2021

Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation.

Mikhail Usvyatsov, Anastasia Makarova, Rafael Ballester-Ripoll, Maxim V. Rakhuba, Andreas Krause, Konrad Schindler

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Spectral Tensor Train Parameterization of Deep Learning Layers.

Anton Obukhov, Maxim V. Rakhuba, Alexander Liniger, Zhiwu Huang, Stamatios Georgoulis, Dengxin Dai, Luc Van Gool

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Low rank tensor approximation of singularly perturbed partial differential equations in one dimension.

Carlo Marcati, Maxim V. Rakhuba, Johan E. M. Ulander

CoRR, 2020

T-Basis: a Compact Representation for Neural Networks.

Anton Obukhov, Maxim V. Rakhuba, Stamatios Georgoulis, Menelaos Kanakis, Dengxin Dai, Luc Van Gool

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

Low-rank Riemannian eigensolver for high-dimensional Hamiltonians.

Maxim V. Rakhuba, Alexander Novikov, Ivan V. Oseledets

J. Comput. Phys., 2019

2018

Jacobi-Davidson Method on Low-Rank Matrix Manifolds.

M. V. Rakhuba, Ivan V. Oseledets

SIAM J. Sci. Comput., 2018

Alternating Least Squares as Moving Subspace Correction.

Ivan V. Oseledets, Maxim V. Rakhuba, André Uschmajew

SIAM J. Numer. Anal., 2018

2017

Vico-Greengard-Ferrando quadratures in the tensor solver for integral equations.

Valentin Khrulkov, M. V. Rakhuba, Ivan V. Oseledets

CoRR, 2017

QTT-finite-element approximation for multiscale problems I: model problems in one dimension.

Vladimir A. Kazeev, Ivan V. Oseledets, Maksim Rakhuba, Christoph Schwab

Adv. Comput. Math., 2017

2016

Grid-based electronic structure calculations: The tensor decomposition approach.

M. V. Rakhuba, Ivan V. Oseledets

J. Comput. Phys., 2016

2015

Fast Multidimensional Convolution in Low-Rank Tensor Formats via Cross Approximation.

M. V. Rakhuba, Ivan V. Oseledets

SIAM J. Sci. Comput., 2015

Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition.

Vadim Lebedev, Yaroslav Ganin, Maksim Rakhuba, Ivan V. Oseledets, Victor S. Lempitsky

Proceedings of the 3rd International Conference on Learning Representations, 2015