Follow
Rudrajit Das
Rudrajit Das
CS PhD student at UT Austin
Verified email at utexas.edu - Homepage
Title
Cited by
Cited by
Year
Faster Non-Convex Federated Learning via Global and Local Momentum
R Das, A Acharya, A Hashemi, S Sanghavi, IS Dhillon, U Topcu
Uncertainty in Artificial Intelligence (UAI) 2022, 496-506, 2022
71*2022
On the unreasonable effectiveness of federated averaging with heterogeneous data
J Wang, R Das, G Joshi, S Kale, Z Xu, T Zhang
arXiv preprint arXiv:2206.04723, 2022
332022
On the benefits of multiple gossip steps in communication-constrained decentralized federated learning
A Hashemi, A Acharya, R Das, H Vikalo, S Sanghavi, I Dhillon
IEEE Transactions on Parallel and Distributed Systems 33 (11), 2727-2739, 2021
33*2021
On the separability of classes with the cross-entropy loss function
R Das, S Chaudhuri
arXiv preprint arXiv:1909.06930, 2019
152019
Beyond uniform lipschitz condition in differentially private optimization
R Das, S Kale, Z Xu, T Zhang, S Sanghavi
International Conference on Machine Learning (ICML) 2023, 2023
132023
Differentially Private Federated Learning with Normalized Updates
R Das, A Hashemi, IS Dhillon
OPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop), 2022
10*2022
Sparse kernel PCA for outlier detection
R Das, A Golatkar, SP Awate
2018 17th IEEE International Conference on Machine Learning and Applications …, 2018
62018
Privacy-preserving federated learning via normalized (instead of clipped) updates
R Das, A Hashemi, S Sanghavi, IS Dhillon
arXiv preprint arXiv:2106.07094, 2021
52021
Nonlinear blind compressed sensing under signal-dependent noise
R Das, A Rajwade
2019 IEEE International Conference on Image Processing (ICIP), 2030-2034, 2019
5*2019
Understanding Self-Distillation in the Presence of Label Noise
R Das, S Sanghavi
International Conference on Machine Learning (ICML) 2023, 2023
22023
Towards Quantifying the Preconditioning Effect of Adam
R Das, N Agarwal, S Sanghavi, IS Dhillon
arXiv preprint arXiv:2402.07114, 2024
2024
Understanding the Training Speedup from Sampling with Approximate Losses
R Das, X Chen, B Ieong, P Bansal, S Sanghavi
arXiv preprint arXiv:2402.07052, 2024
2024
DISCO: efficient unsupervised decoding for discrete natural language problems via convex relaxation
A Acharya, R Das
arXiv preprint arXiv:2107.05380, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–13