Agniva Chowdhury

Publications/ Preprints


  1. Prithvi Dixit, Sahil Joshi, Agniva Chowdhury, Anshumali Shrivastava, Joseph E. Gonzalez, Ion Stoica, Kumar Krishna Agrawal, and Aditya Desai. Long-Context Language Models Require Extreme Sparsity in Context Dimension. In Advances in Neural Information Processing Systems (NeurIPS), 2026 (to appear).

  2. Sahil Joshi, Agniva Chowdhury, Amar Kanakamedala, Ekam Singh, Evan Tu, and Anshumali Shrivastava. RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts. In Proceedings of the 14th International Conference on Learning Representations (ICLR), 2026.

  3. Agniva Chowdhury and Pradeep Ramuhalli. A Provably Accurate Randomized Sampling Algorithm for Logistic Regression. In Proceedings of the 38th AAAI Conference on Artificial Intelligence, 2024.

  4. Shreyas Fadnavis, Agniva Chowdhury, Joshua Batson, Petros Drineas, and Eleftherios Garyfallidis. Patch2Self2: Self-supervised Denoising on Coresets via Matrix Sketching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

  5. Aritra Bose, Myson Burch, Agniva Chowdhury, Peristera Paschou, and Petros Drineas. Structure-informed Clustering for Population Stratification in Association Studies. BMC Bioinformatics, 24(1), p. 411, 2023.

  6. Frank Liu, and Agniva Chowdhury. Deep Learning with Physics Priors as Generalized Regularizers. NeurIPS AI for Science Workshop, 2023.

  7. Agniva Chowdhury, Gregory Dexter, Palma London Haim Avron, and Petros Drineas. Faster Randomized Interior Point Methods for Tall/Wide Linear Programs. Journal of Machine Learning Research (JMLR), 23(336):1−48, 2022.

  8. Gregory Dexter, Agniva Chowdhury, Haim Avron, and Petros Drineas. On the Convergence of Inexact Predictor-Corrector Methods for Linear Programming. In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022. Selected for long presentation.

  9. Agniva Chowdhury, Aritra Bose, Samson Zhou, David P. Woodruff, and Petros Drineas,. A Fast, Provably Accurate Approximation Algorithm for Sparse Principal Component Analysis Reveals Human Genetic Variation Across the World. In Proceedings of the 26th Annual Conference on Research in Computational Molecular Biology (RECOMB), 2022.

  10. Agniva Chowdhury, Palma London, Haim Avron, and Petros Drineas. Faster Randomized Infeasible Interior Point Methods for Tall/Wide Linear Programs. In Advances in Neural Information Processing Systems (NeurIPS), 2020.

  11. Agniva Chowdhury, Petros Drineas, David P. Woodruff, and Samson Zhou. Approximation Algorithms for Sparse Principal Component Analysis. arXiv:2006.12748, 2020.

  12. Aritra Bose, Myson C. Burch, Agniva Chowdhury, Peristera Paschou, and Petros Drineas. CluStrat: A Structure Informed Clustering Strategy for Population Stratification. In Proceedings of the 24th Annual Conference on Research in Computational Molecular Biology (RECOMB), 2020.

  13. Agniva Chowdhury, Jiasen Yang, and Petros Drineas. Randomized Iterative Algorithms for Fisher Discriminant Analysis. In Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), 2019. Selected for oral presentation.

  14. Agniva Chowdhury, Jiasen Yang, and Petros Drineas. Structural Conditions for Projection-Cost Preservation via Randomized Matrix Multiplication. Linear Algebra and its Applications, 573, pp. 144-165, 2019.

  15. Agniva Chowdhury, Jiasen Yang, and Petros Drineas. An Iterative, Sketching-based Framework for Ridge Regression. In Proceedings of the 35th International Conference on Machine Learning (ICML), 2018.