conftrace_

local gradient estimator

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

finite sum (1) variance reduced (1) stochastic variance reduced gradient (1) privacy-utility trade-off (1) communication compression (1) condition number (1) strongly convex (1) decentralized optimization (1) differential privacy (1) federated learning (1)

Papers

Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers ICML 2024 SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression NeurIPS 2022