| Multi-domain translation between single-cell imaging and sequencing data using autoencoders KD Yang, A Belyaeva, S Venkatachalapathy, K Damodaran, A Katcoff, ... Nature communications 12 (1), 31, 2021 | 162 | 2021 |
| Overparameterized neural networks implement associative memory A Radhakrishnan, M Belkin, C Uhler Proceedings of the National Academy of Sciences 117 (44), 27162-27170, 2020 | 138* | 2020 |
| Mechanism for feature learning in neural networks and backpropagation-free machine learning models A Radhakrishnan, D Beaglehole, P Pandit, M Belkin Science, 2024 | 79* | 2024 |
| Machine learning for nuclear mechano-morphometric biomarkers in cancer diagnosis A Radhakrishnan, K Damodaran, AC Soylemezoglu, C Uhler, ... Scientific reports 7 (1), 17946, 2017 | 61 | 2017 |
| Causal network models of SARS-CoV-2 expression and aging to identify candidates for drug repurposing A Belyaeva, L Cammarata, A Radhakrishnan, C Squires, KD Yang, ... Nature communications 12 (1), 1024, 2021 | 59 | 2021 |
| Cross-modal autoencoder framework learns holistic representations of cardiovascular state A Radhakrishnan, SF Friedman, S Khurshid, K Ng, P Batra, SA Lubitz, ... Nature Communications 14 (1), 2436, 2023 | 51 | 2023 |
| Simple, fast, and flexible framework for matrix completion with infinite width neural networks A Radhakrishnan, G Stefanakis, M Belkin, C Uhler Proceedings of the National Academy of Sciences 119 (16), e2115064119, 2022 | 26 | 2022 |
| Wide and deep neural networks achieve consistency for classification A Radhakrishnan, M Belkin, C Uhler Proceedings of the National Academy of Sciences 120 (14), e2208779120, 2023 | 24 | 2023 |
| Increasing depth leads to U-shaped test risk in over-parameterized convolutional networks E Nichani, A Radhakrishnan, C Uhler arXiv preprint arXiv:2010.09610, 2020 | 23* | 2020 |
| Quadratic models for understanding neural network dynamics L Zhu, C Liu, A Radhakrishnan, M Belkin arXiv preprint arXiv:2205.11787, 2022 | 19 | 2022 |
| Counting Markov equivalence classes for DAG models on trees A Radhakrishnan, L Solus, C Uhler Discrete Applied Mathematics 244, 170-185, 2018 | 19 | 2018 |
| Mechanism of feature learning in convolutional neural networks D Beaglehole, A Radhakrishnan, P Pandit, M Belkin arXiv preprint arXiv:2309.00570, 2023 | 17 | 2023 |
| Transfer learning with kernel methods A Radhakrishnan, M Ruiz Luyten, N Prasad, C Uhler Nature Communications 14 (1), 5570, 2023 | 16 | 2023 |
| Counting Markov equivalence classes by number of immoralities A Radhakrishnan, L Solus, C Uhler arXiv preprint arXiv:1611.07493, 2016 | 15 | 2016 |
| Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning L Zhu, C Liu, A Radhakrishnan, M Belkin arXiv preprint arXiv:2306.04815, 2023 | 14 | 2023 |
| Patchnet: interpretable neural networks for image classification A Radhakrishnan, C Durham, A Soylemezoglu, C Uhler arXiv preprint arXiv:1705.08078, 2017 | 14 | 2017 |
| A mechanism for producing aligned latent spaces with autoencoders S Jain, A Radhakrishnan, C Uhler arXiv preprint arXiv:2106.15456, 2021 | 11 | 2021 |
| Linear convergence of generalized mirror descent with time-dependent mirrors A Radhakrishnan, M Belkin, C Uhler arXiv preprint arXiv:2009.08574, 2020 | 9* | 2020 |
| Multi-domain translation between single-cell imaging and sequencing data using autoencoders. Nat. Commun. 12, 31 KD Yang, A Belyaeva, S Venkatachalapathy, K Damodaran, A Katcoff, ... | 7 | 2021 |
| Linear Recursive Feature Machines provably recover low-rank matrices A Radhakrishnan, M Belkin, D Drusvyatskiy arXiv preprint arXiv:2401.04553, 2024 | 6 | 2024 |
Caroline UhlerMassachusetts Institute of TechnologyVerified email at mit.edu
