| Speeding-up convolutional neural networks using fine-tuned cp-decomposition V Lebedev, Y Ganin, M Rakhuba, I Oseledets, V Lempitsky arXiv preprint arXiv:1412.6553, 2014 | 1136 | 2014 |
| Calculating vibrational spectra of molecules using tensor train decomposition M Rakhuba, I Oseledets The Journal of chemical physics 145 (12), 2016 | 70 | 2016 |
| Fast multidimensional convolution in low-rank tensor formats via cross approximation MV Rakhuba, IV Oseledets SIAM Journal on Scientific Computing 37 (2), A565-A582, 2015 | 64 | 2015 |
| QTT-finite-element approximation for multiscale problems I: model problems in one dimension V Kazeev, I Oseledets, M Rakhuba, C Schwab Advances in Computational Mathematics 43, 411-442, 2017 | 32* | 2017 |
| T-basis: a compact representation for neural networks A Obukhov, M Rakhuba, S Georgoulis, M Kanakis, D Dai, L Van Gool International Conference on Machine Learning, 7392-7404, 2020 | 29 | 2020 |
| Grid-based electronic structure calculations: The tensor decomposition approach MV Rakhuba, IV Oseledets Journal of Computational Physics 312, 19-30, 2016 | 27 | 2016 |
| Alternating least squares as moving subspace correction IV Oseledets, MV Rakhuba, A Uschmajew SIAM Journal on Numerical Analysis 56 (6), 3459-3479, 2018 | 21 | 2018 |
| Speeding-up convolutional neural networks using fine-tuned cp-decomposition. arXiv 2014 V Lebedev, Y Ganin, M Rakhuba, I Oseledets, V Lempitsky arXiv preprint arXiv:1412.6553, 0 | 20 | |
| Low-rank Riemannian eigensolver for high-dimensional Hamiltonians M Rakhuba, A Novikov, I Oseledets Journal of Computational Physics 396, 718-737, 2019 | 15 | 2019 |
| Tensor rank bounds for point singularities in ℝ3 C Marcati, M Rakhuba, C Schwab Advances in Computational Mathematics 48 (3), 18, 2022 | 13 | 2022 |
| Spectral tensor train parameterization of deep learning layers A Obukhov, M Rakhuba, A Liniger, Z Huang, S Georgoulis, D Dai, ... International Conference on Artificial Intelligence and Statistics, 3547-3555, 2021 | 13 | 2021 |
| Jacobi--Davidson method on low-rank matrix manifolds MV Rakhuba, IV Oseledets SIAM Journal on Scientific Computing 40 (2), A1149-A1170, 2018 | 12 | 2018 |
| Towards practical control of singular values of convolutional layers A Senderovich, E Bulatova, A Obukhov, M Rakhuba Advances in Neural Information Processing Systems 35, 10918-10930, 2022 | 11 | 2022 |
| Quantized tensor FEM for multiscale problems: diffusion problems in two and three dimensions V Kazeev, I Oseledets, MV Rakhuba, C Schwab Multiscale Modeling & Simulation 20 (3), 893-935, 2022 | 11 | 2022 |
| Robust discretization in quantized tensor train format for elliptic problems in two dimensions AV Chertkov, IV Oseledets, MV Rakhuba arXiv preprint arXiv:1612.01166, 2016 | 9 | 2016 |
| Black-box solver for multiscale modelling using the QTT format IV Oseledets, MV Rakhuba, AV Chertkov Proc. ECCOMAS. Crete Island, Greece, 2016 | 7 | 2016 |
| Automatic differentiation for Riemannian optimization on low-rank matrix and tensor-train manifolds A Novikov, M Rakhuba, I Oseledets SIAM Journal on Scientific Computing 44 (2), A843-A869, 2022 | 6 | 2022 |
| Cherry-picking gradients: Learning low-rank embeddings of visual data via differentiable cross-approximation M Usvyatsov, A Makarova, R Ballester-Ripoll, M Rakhuba, A Krause, ... Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 6 | 2021 |
| Robust solver in a quantized tensor format for three-dimensional elliptic problems M Rakhuba SAM Research Report 2019, 2019 | 6* | 2019 |
| Tensor rank bounds and explicit QTT representations for the inverses of circulant matrices L Vysotsky, M Rakhuba Numerical Linear Algebra with Applications 30 (3), e2461, 2023 | 5 | 2023 |
Ivan OseledetsAIRI; Skolkovo Institute of Science and TechnologyVerified email at skoltech.ru