| On the information bottleneck theory of deep learning AM Saxe, Y Bansal, J Dapello, M Advani, A Kolchinsky, BD Tracey, ... Journal of Statistical Mechanics: Theory and Experiment 2019 (12), 124020, 2019 | 601 | 2019 |
| High-dimensional dynamics of generalization error in neural networks MS Advani, AM Saxe, H Sompolinsky Neural Networks 132, 428-446, 2020 | 491 | 2020 |
| Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup S Goldt, M Advani, AM Saxe, F Krzakala, L Zdeborová Advances in neural information processing systems 32, 2019 | 159 | 2019 |
| Statistical mechanics of complex neural systems and high dimensional data M Advani, S Lahiri, S Ganguli Journal of Statistical Mechanics: Theory and Experiment 2013 (03), P03014, 2013 | 87 | 2013 |
| Statistical physics of community ecology: a cavity solution to MacArthur’s consumer resource model M Advani, G Bunin, P Mehta Journal of Statistical Mechanics: Theory and Experiment 2018 (3), 033406, 2018 | 81 | 2018 |
| Dimensionality compression and expansion in deep neural networks S Recanatesi, M Farrell, M Advani, T Moore, G Lajoie, E Shea-Brown arXiv preprint arXiv:1906.00443, 2019 | 77 | 2019 |
| Energy–entropy competition and the effectiveness of stochastic gradient descent in machine learning Y Zhang, AM Saxe, MS Advani, AA Lee Molecular Physics 116 (21-22), 3214-3223, 2018 | 76 | 2018 |
| Statistical mechanics of optimal convex inference in high dimensions M Advani, S Ganguli Physical Review X 6 (3), 031034, 2016 | 66 | 2016 |
| Organizing memories for generalization in complementary learning systems W Sun, M Advani, N Spruston, A Saxe, JE Fitzgerald Nature neuroscience 26 (8), 1438-1448, 2023 | 42 | 2023 |
| An equivalence between high dimensional bayes optimal inference and m-estimation M Advani, S Ganguli Advances in Neural Information Processing Systems 29, 2016 | 21 | 2016 |
| Minnorm training: an algorithm for training over-parameterized deep neural networks Y Bansal, M Advani, DD Cox, AM Saxe arXiv preprint arXiv:1806.00730, 2018 | 18 | 2018 |
| Position and orientation inference via on-board triangulation M Advani, DS Weile Plos one 12 (6), e0180089, 2017 | 6 | 2017 |
| New role for circuit expansion for learning in neural networks J Steinberg, M Advani, H Sompolinsky Physical Review E 103 (2), 022404, 2021 | 3 | 2021 |
| How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks E Littwin, O Saremi, M Advani, V Thilak, P Nakkiran, C Huang, J Susskind arXiv preprint arXiv:2407.03475, 2024 | | 2024 |
| Step-by-Step Diffusion: An Elementary Tutorial P Nakkiran, A Bradley, H Zhou, M Advani arXiv preprint arXiv:2406.08929, 2024 | | 2024 |
Andrew SaxeProfessor, Gatsby Unit & Sainsbury Wellcome Centre, UCLVerified email at ucl.ac.uk
