On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data.
Trans. Mach. Learn. Res., 2024
Retraining with Predicted Hard Labels Provably Increases Model Accuracy.
CoRR, 2024
Towards Quantifying the Preconditioning Effect of Adam.
CoRR, 2024
Understanding the Training Speedup from Sampling with Approximate Losses.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Understanding Self-Distillation in the Presence of Label Noise.
Proceedings of the International Conference on Machine Learning, 2023
Beyond Uniform Lipschitz Condition in Differentially Private Optimization.
Proceedings of the International Conference on Machine Learning, 2023
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Federated Learning.
IEEE Trans. Parallel Distributed Syst., 2022
Faster non-convex federated learning via global and local momentum.
Proceedings of the Uncertainty in Artificial Intelligence, 2022
DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation.
CoRR, 2021
DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning.
CoRR, 2021
Improved Convergence Rates for Non-Convex Federated Learning with Compression.
CoRR, 2020
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization.
CoRR, 2020
On the Separability of Classes with the Cross-Entropy Loss Function.
CoRR, 2019
Nonlinear Blind Compressed Sensing Under Signal-Dependent Noise.
Proceedings of the 2019 IEEE International Conference on Image Processing, 2019
Sparse Kernel PCA for Outlier Detection.
Proceedings of the 17th IEEE International Conference on Machine Learning and Applications, 2018