| Mechanism for feature learning in neural networks and backpropagation-free machine learning models A Radhakrishnan*, D Beaglehole*, P Pandit, M Belkin Science, 2024 | 81* | 2024 |
| Selenophosphate synthetase 1 is an essential protein with roles in regulation of redox homoeostasis in mammals R Tobe, BA Carlson, JH Huh, NP Castro, XM Xu, PA Tsuji, SG Lee, ... Biochemical Journal 473 (14), 2141-2154, 2016 | 42 | 2016 |
| On the inconsistency of kernel ridgeless regression in fixed dimensions D Beaglehole, M Belkin, P Pandit SIAM Journal on Mathematics of Data Science 5 (4), 854-872, 2023 | 26* | 2023 |
| Mechanism of feature learning in convolutional neural networks D Beaglehole*, A Radhakrishnan*, P Pandit, M Belkin arXiv preprint arXiv:2309.00570, 2023 | 17 | 2023 |
| Learning to hash robustly, guaranteed A Andoni, D Beaglehole International Conference on Machine Learning, 599-618, 2022 | 15 | 2022 |
| Sampling Equilibria: Fast No-Regret Learning in Structured Games D Beaglehole, M Hopkins, D Kane, S Liu, S Lovett Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms …, 2023 | 12* | 2023 |
| Average gradient outer product as a mechanism for deep neural collapse D Beaglehole, P Súkeník, M Mondelli, M Belkin 38th Conference on Neural Information Processing Systems (NeurIPS), 2024 | 10 | 2024 |
| Gradient descent induces alignment between weights and the pre-activation tangents for deep non-linear networks D Beaglehole, I Mitliagkas, A Agarwala High-dimensional Learning Dynamics 2024: The Emergence of Structure and …, 2024 | 4* | 2024 |
| Emergence in non-neural models: grokking modular arithmetic via average gradient outer product N Mallinar, D Beaglehole, L Zhu, A Radhakrishnan, P Pandit, M Belkin arXiv preprint arXiv:2407.20199, 2024 | 3 | 2024 |
| Feature learning as alignment: a structural property of gradient descent in non-linear neural networks D Beaglehole, I Mitliagkas, A Agarwala Transactions on Machine Learning Research, 2024 | 1 | 2024 |
| Aggregate and conquer: detecting and steering LLM concepts by combining nonlinear predictors over multiple layers D Beaglehole, A Radhakrishnan, E Boix-Adserà, M Belkin arXiv preprint arXiv:2502.03708, 2025 | | 2025 |
| Fast, optimal, and dynamic electoral campaign budgeting by a generalized Colonel Blotto game T Valles, D Beaglehole arXiv preprint arXiv:2406.15714, 2024 | | 2024 |