| Testing ising models C Daskalakis, N Dikkala, G Kamath IEEE Transactions on Information Theory 65 (11), 6829-6852, 2019 | 112 | 2019 |
| Minimax estimation of conditional moment models N Dikkala, G Lewis, L Mackey, V Syrgkanis Advances in Neural Information Processing Systems 33, 12248-12262, 2020 | 100 | 2020 |
| From soft classifiers to hard decisions: How fair can we be? R Canetti, A Cohen, N Dikkala, G Ramnarayan, S Scheffler, A Smith Proceedings of the conference on fairness, accountability, and transparency …, 2019 | 58 | 2019 |
| Tight hardness results for maximum weight rectangles A Backurs, N Dikkala, C Tzamos arXiv preprint arXiv:1602.05837, 2016 | 57 | 2016 |
| Regression from dependent observations C Daskalakis, N Dikkala, I Panageas Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing …, 2019 | 38 | 2019 |
| Testing symmetric markov chains from a single trajectory C Daskalakis, N Dikkala, N Gravin Conference On Learning Theory, 385-409, 2018 | 35 | 2018 |
| Learning from weakly dependent data under dobrushin’s condition Y Dagan, C Daskalakis, N Dikkala, S Jayanti Conference on Learning Theory, 914-928, 2019 | 33 | 2019 |
| Do more negative samples necessarily hurt in contrastive learning? P Awasthi, N Dikkala, P Kamath International conference on machine learning, 1101-1116, 2022 | 30 | 2022 |
| Concentration of multilinear functions of the Ising model with applications to network data C Daskalakis, N Dikkala, G Kamath Advances in Neural Information Processing Systems 30, 2017 | 29 | 2017 |
| Hogwild!-gibbs can be panaccurate C Daskalakis, N Dikkala, S Jayanti Advances in Neural Information Processing Systems 31, 2018 | 19 | 2018 |
| Learning Ising models from one or multiple samples Y Dagan, C Daskalakis, N Dikkala, AV Kandiros Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing …, 2021 | 18 | 2021 |
| Logistic regression with peer-group effects via inference in higher-order Ising models C Daskalakis, N Dikkala, I Panageas International Conference on Artificial Intelligence and Statistics, 3653-3663, 2020 | 14 | 2020 |
| Estimating ising models from one sample Y Dagan, C Daskalakis, N Dikkala, AV Kandiros arXiv preprint arXiv:2004.09370, 2020 | 13 | 2020 |
| A theoretical view on sparsely activated networks C Baykal, N Dikkala, R Panigrahy, C Rashtchian, X Wang Advances in Neural Information Processing Systems 35, 30071-30084, 2022 | 9 | 2022 |
| Statistical estimation from dependent data V Kandiros, Y Dagan, N Dikkala, S Goel, C Daskalakis International Conference on Machine Learning, 5269-5278, 2021 | 9 | 2021 |
| Can Credit Increase Revenue? N Dikkala, É Tardos Web and Internet Economics: 9th International Conference, WINE 2013 …, 2013 | 8 | 2013 |
| For manifold learning, deep neural networks can be locality sensitive hash functions N Dikkala, G Kaplun, R Panigrahy arXiv preprint arXiv:2103.06875, 2021 | 7 | 2021 |
| On the benefits of learning to route in mixture-of-experts models N Dikkala, N Ghosh, R Meka, R Panigrahy, N Vyas, X Wang Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023 | 6 | 2023 |
| ReMI: A Dataset for Reasoning with Multiple Images M Kazemi, N Dikkala, A Anand, P Devic, I Dasgupta, F Liu, B Fatemi, ... arXiv preprint arXiv:2406.09175, 2024 | 1 | 2024 |
| Alternating updates for efficient transformers C Baykal, D Cutler, N Dikkala, N Ghosh, R Panigrahy, X Wang Advances in Neural Information Processing Systems 36, 2024 | 1 | 2024 |
