1.6k citations · 3.6k across the 48 of their papers we have counts for
3 papers · 1 filter
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale +4
Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of the data across different clients which gives rise to the client drift phenomenon. In…
Estimating Training Data Influence by Tracing Gradient Descent
Garima Pruthi, Frederick Liu, Mukund Sundararajan +1
We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. The idea is to trace how the loss on the test point changes…
A Deep Conditioning Treatment of Neural Networks
Naman Agarwal, Pranjal Awasthi, Satyen Kale
We study the role of depth in training randomly initialized overparameterized neural networks. We give a general result showing that depth improves trainability of neural networks…