Rudrajit Das

25 papers A* 5A 1B 1C 1Journal 17
YearRankTypeTitle / Venue / Authors
2026 J jnl
Less is More: Convergence Benefits of Fewer Data Weight Updates over Longer Horizon.
CoRR
Rudrajit Das, Neel Patel, Meisam Razaviyayn, Vahab Mirrokni
2025 A* conf
Retraining with Predicted Hard Labels Provably Increases Model Accuracy.
ICML
Rudrajit Das, Inderjit S. Dhillon, Alessandro Epasto, Adel Javanmard, Jieming Mao, Vahab Mirrokni, Sujay Sanghavi, Peilin Zhong
2025 J jnl
Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing.
CoRR
Adel Javanmard, Rudrajit Das, Alessandro Epasto, Vahab Mirrokni
2025 A* conf
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting.
ICML
Sunny Sanyal, Hayden Prairie, Rudrajit Das, Ali Kavis, Sujay Sanghavi
2025 J jnl
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting.
CoRR
Sunny Sanyal, Hayden Prairie, Rudrajit Das, Ali Kavis, Sujay Sanghavi
2024 J jnl
On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data.
Trans. Mach. Learn. Res.
Jianyu Wang, Rudrajit Das, Gauri Joshi, Satyen Kale, Zheng Xu, Tong Zhang
2024 J jnl
Retraining with Predicted Hard Labels Provably Increases Model Accuracy.
CoRR
Rudrajit Das, Inderjit S. Dhillon, Alessandro Epasto, Adel Javanmard, Jieming Mao, Vahab Mirrokni, Sujay Sanghavi, Peilin Zhong
2024 J jnl
Towards Quantifying the Preconditioning Effect of Adam.
CoRR
Rudrajit Das, Naman Agarwal, Sujay Sanghavi, Inderjit S. Dhillon
2024 A* conf
Understanding the Training Speedup from Sampling with Approximate Losses.
ICML
Rudrajit Das, Xi Chen, Bertram Ieong, Parikshit Bansal, Sujay Sanghavi
2024 J jnl
Understanding the Training Speedup from Sampling with Approximate Losses.
CoRR
Rudrajit Das, Xi Chen, Bertram Ieong, Parikshit Bansal, Sujay Sanghavi
2023 A* conf
Beyond Uniform Lipschitz Condition in Differentially Private Optimization.
ICML
Rudrajit Das, Satyen Kale, Zheng Xu, Tong Zhang, Sujay Sanghavi
2023 A* conf
Understanding Self-Distillation in the Presence of Label Noise.
ICML
Rudrajit Das, Sujay Sanghavi
2023 J jnl
Understanding Self-Distillation in the Presence of Label Noise.
CoRR
Rudrajit Das, Sujay Sanghavi
2022 J jnl
Beyond Uniform Lipschitz Condition in Differentially Private Optimization.
CoRR
Rudrajit Das, Satyen Kale, Zheng Xu, Tong Zhang, Sujay Sanghavi
2022 A conf
Faster non-convex federated learning via global and local momentum.
UAI
Rudrajit Das, Anish Acharya, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon, Ufuk Topcu
2022 J jnl
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Federated Learning.
IEEE Trans. Parallel Distributed Syst.
Abolfazl Hashemi, Anish Acharya, Rudrajit Das, Haris Vikalo, Sujay Sanghavi, Inderjit S. Dhillon
2022 J jnl
On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data.
CoRR
Jianyu Wang, Rudrajit Das, Gauri Joshi, Satyen Kale, Zheng Xu, Tong Zhang
2021 J jnl
DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation.
CoRR
Anish Acharya, Rudrajit Das
2021 J jnl
DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning.
CoRR
Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon
2020 J jnl
Improved Convergence Rates for Non-Convex Federated Learning with Compression.
CoRR
Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon
2020 J jnl
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization.
CoRR
Abolfazl Hashemi, Anish Acharya, Rudrajit Das, Haris Vikalo, Sujay Sanghavi, Inderjit S. Dhillon
2019 B conf
Nonlinear Blind Compressed Sensing Under Signal-Dependent Noise.
ICIP
Rudrajit Das, Ajit Rajwade
2019 J jnl
On the Separability of Classes with the Cross-Entropy Loss Function.
CoRR
Rudrajit Das, Subhasis Chaudhuri
2018 C conf
Sparse Kernel PCA for Outlier Detection.
ICMLA
Rudrajit Das, Aditya Golatkar, Suyash P. Awate
2018 J jnl
Sparse Kernel PCA for Outlier Detection.
CoRR
Rudrajit Das, Aditya Golatkar, Suyash P. Awate