Joshi, Nirmit

8 publications

COLT 2025 A Theory of Learning with Autoregressive Chain of Thought Nirmit Joshi, Gal Vardi, Adam Block, Surbhi Goel, Zhiyuan Li, Theodor Misiakiewicz, Nathan Srebro

ICLR 2025 Exact Community Recovery Under Side Information: Optimality of Spectral Algorithms Julia Gaudio, Nirmit Joshi

NeurIPS 2025 Learning Single Index Models via Harmonic Decomposition Nirmit Joshi, Hugo Koubbi, Theodor Misiakiewicz, Nathan Srebro

ICLR 2024 Noisy Interpolation Learning with Shallow Univariate ReLU Networks Nirmit Joshi, Gal Vardi, Nathan Srebro

NeurIPS 2024 On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries Nirmit Joshi, Theodor Misiakiewicz, Nathan Srebro

COLT 2024 The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication Kumar Kshitij Patel, Margalit Glasgow, Ali Zindari, Lingxiao Wang, Sebastian U Stich, Ziheng Cheng, Nirmit Joshi, Nathan Srebro

COLT 2023 Community Detection in the Hypergraph SBM: Exact Recovery Given the Similarity Matrix Julia Gaudio, Nirmit Joshi

ICMLW 2023 On the Still Unreasonable Effectiveness of Federated Averaging for Heterogeneous Distributed Learning Kumar Kshitij Patel, Margalit Glasgow, Lingxiao Wang, Nirmit Joshi, Nathan Srebro