Follow
Shashank Rajput
Shashank Rajput
Research Scientist, MosaicML (Databricks)
Verified email at databricks.com - Homepage
Title
Cited by
Year
Maestro: Uncovering Low-Rank Structures via Trainable Decomposition
S Horvath, S Laskaridis, S Rajput, H Wang
arXiv preprint arXiv:2308.14929, 2023
12023
The Expressive Power of Tuning Only the Normalization Layers
A Giannou, S Rajput, D Papailiopoulos
The Thirty Sixth Annual Conference on Learning Theory, 4130-4131, 2023
22023
Large-Scale SGD Algorithms and the Expressive Power of Modern Neural Networks
S Rajput
The University of Wisconsin-Madison, 2023
2023
The Expressive Power of Tuning Only the Norm Layers
A Giannou, S Rajput, D Papailiopoulos
Conference on Learning Theory (COLT), 2023
42023
Recommender Systems with Generative Retrieval
S Rajput, N Mehta, A Singh, R Keshavan, T Vu, L Heldt, L Hong, Y Tay, ...
Advances in Neural Information Processing Systems (NeurIPS), 2023
242023
Looped Transformers as Programmable Computers
A Giannou, S Rajput, J Sohn, K Lee, JD Lee, D Papailiopoulos
International Conference on Machine Learning (ICML), 2023
462023
Lift: Language-interfaced fine-tuning for non-language machine learning tasks
T Dinh, Y Zeng, R Zhang, Z Lin, M Gira, S Rajput, J Sohn, ...
Advances in Neural Information Processing Systems (NeurIPS), 2022
562022
Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
T Dinh, J Sohn, S Rajput, T Ossowski, Y Ming, J Hu, D Papailiopoulos, ...
EMNLP (Findings), 2022
12022
Finding everything within random binary networks
K Sreenivasan, S Rajput, J Sohn, D Papailiopoulos
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
15*2022
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond
C Yun, S Rajput, S Sra
International Conference on Learning Representations (ICLR), 2022
332022
Permutation-Based SGD: Is Random Optimal?
S Rajput, K Lee, D Papailiopoulos
International Conference on Learning Representations (ICLR), 2022
162022
An exponential improvement on the memorization capacity of deep threshold networks
S Rajput, K Sreenivasan, D Papailiopoulos, A Karbasi
Advances in Neural Information Processing Systems (NeurIPS), 2021
152021
Closing the convergence gap of SGD without replacement
S Rajput, A Gupta, D Papailiopoulos
International Conference on Machine Learning (ICML), 2020
552020
Attack of the tails: Yes, you really can backdoor federated learning
H Wang, K Sreenivasan, S Rajput, H Vishwakarma, S Agarwal, J Sohn, ...
Advances in Neural Information Processing Systems (NeurIPS), 2020
4842020
Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient
A Pensia, S Rajput, A Nagle, H Vishwakarma, D Papailiopoulos
Advances in Neural Information Processing Systems (NeurIPS), 2020
922020
Does data augmentation lead to positive margin?
S Rajput, Z Feng, Z Charles, PL Loh, D Papailiopoulos
International Conference on Machine Learning (ICML), 2019
412019
Convergence and Margin of Adversarial Training on Separable Data
Z Charles, S Rajput, S Wright, D Papailiopoulos
arXiv preprint arXiv:1905.09209, 2019
182019
DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation
S Rajput, H Wang, Z Charles, D Papailiopoulos
Advances in Neural Information Processing Systems (NeurIPS), 2019
1172019
SUPER SEEDS: extreme model compression by trading off storage with compute
N Lee, S Rajput, J Sohnw, H Wangc, A Naglew, EP Xingmp, K Leew, ...
The system can't perform the operation now. Try again later.
Articles 1–19