125 citations · 182 across the 14 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.LG2021
Accelerate Distributed Stochastic Descent for Nonconvex Optimization with Momentum
Guojing Cong, Tianyi Liu
Momentum method has been used extensively in optimizers for deep learning. Recent studies show that distributed training through K-step averaging has many nice properties. We propo…
cs.RO2021
GODSAC*: Graph Optimized DSAC* for Robot Relocalization
Alphonsus Adu-Bredu, Noah Del Coro, Tianyi Liu
Deep learning based camera pose estimation from monocular camera images has seen a recent uptake in Visual SLAM research. Even though such pose estimation approaches have excellent…
cs.LG2021★ 2 cited
Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization
Tianyi Liu, Yan Li, Song Wei +2
Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems. The theory behind such empirical observations, however, is still largely…