Understanding gradient descent on the edge of stability in deep learning S Arora, Z Li, A Panigrahi International Conference on Machine Learning, 948-1024, 2022 | 94 | 2022 |
Word2Sense: Sparse interpretable word embeddings A Panigrahi, HV Simhadri, C Bhattacharyya Proceedings of the 57th annual meeting of the Association for Computational …, 2019 | 73 | 2019 |
Non-Gaussianity of stochastic gradient noise A Panigrahi, R Somani, N Goyal, P Netrapalli arXiv preprint arXiv:1910.09626, 2019 | 46 | 2019 |
Task-specific skill localization in fine-tuned language models A Panigrahi, N Saunshi, H Zhao, S Arora International Conference on Machine Learning, 27011-27033, 2023 | 37 | 2023 |
Effect of Activation Functions on the Training of Overparametrized Neural Nets A Panigrahi, A Shetty, N Goyal arXiv preprint arXiv:1908.05660, 2019 | 30 | 2019 |
Do transformers parse while predicting the masked word? H Zhao, A Panigrahi, R Ge, S Arora arXiv preprint arXiv:2303.08117, 2023 | 29 | 2023 |
DeepTagRec: A content-cum-user based tag recommendation framework for stack overflow SK Maity, A Panigrahi, S Ghosh, A Banerjee, P Goyal, A Mukherjee Advances in Information Retrieval: 41st European Conference on IR Research …, 2019 | 29 | 2019 |
On the SDEs and scaling rules for adaptive gradient algorithms S Malladi, K Lyu, A Panigrahi, S Arora Advances in Neural Information Processing Systems 35, 7697-7711, 2022 | 26 | 2022 |
Book reading behavior on goodreads can predict the amazon best sellers SK Maity, A Panigrahi, A Mukherjee Proceedings of the 2017 IEEE/ACM International Conference on Advances in …, 2017 | 24 | 2017 |
Trainable transformer in transformer A Panigrahi, S Malladi, M Xia, S Arora arXiv preprint arXiv:2307.01189, 2023 | 18 | 2023 |
Analysis on gradient propagation in batch normalized residual networks A Panigrahi, Y Chen, CCJ Kuo arXiv preprint arXiv:1812.00342, 2018 | 17 | 2018 |
Analyzing social book reading behavior on goodreads and how it predicts amazon best sellers SK Maity, A Panigrahi, A Mukherjee Influence and Behavior Analysis in Social Networks and Social Media, 211-235, 2019 | 13 | 2019 |
Learning and generalization in rnns A Panigrahi, N Goyal Advances in Neural Information Processing Systems 34, 21112-21124, 2021 | 3 | 2021 |
Efficient Stagewise Pretraining via Progressive Subnetworks A Panigrahi, N Saunshi, K Lyu, S Miryoosefi, S Reddi, S Kale, S Kumar arXiv preprint arXiv:2402.05913, 2024 | 1 | 2024 |
Representing Rule-based Chatbots with Transformers D Friedman, A Panigrahi, D Chen arXiv preprint arXiv:2407.10949, 2024 | | 2024 |
Algorithms for Codenames D Friedman, A Panigrahi | | 2021 |
DeepTagRec: A Content-cum-User based Tag Recommendation Framework for Stack Overflow S Kalyan Maity, A Panigrahi, S Ghosh, A Banerjee, P Goyal, A Mukherjee arXiv e-prints, arXiv: 1903.03941, 2019 | | 2019 |
Analyzing Social Book Reading Behavior on Goodreads and how it predicts Amazon Best Sellers S Kalyan Maity, A Panigrahi, A Mukherjee arXiv e-prints, arXiv: 1809.07354, 2018 | | 2018 |
Progressive distillation improves feature learning via implicit curriculum A Panigrahi, B Liu, S Malladi, A Risteski, S Goel ICML 2024 Workshop on Mechanistic Interpretability, 0 | | |