research
∙
01/30/2023
Understanding Self-Distillation in the Presence of Label Noise
Self-distillation (SD) is the process of first training a teacher model ...
share
research
∙
07/07/2021
DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation
In this paper we study test time decoding; an ubiquitous step in almost ...
research
∙
06/13/2021
DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning
In this paper, we focus on facilitating differentially private quantized...
research
∙
12/07/2020
Improved Convergence Rates for Non-Convex Federated Learning with Compression
Federated learning is a new distributed learning paradigm that enables e...
research
∙
11/20/2020
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization
In decentralized optimization, it is common algorithmic practice to have...
research
∙
09/16/2019
On the Separability of Classes with the Cross-Entropy Loss Function
In this paper, we focus on the separability of classes with the cross-en...
research
∙
09/07/2018