Fetching the paper…
Reading the bibliography…
In this note we propose a new variant of the hybrid variance-reduced proximal gradient method in [7] to solve a common stochastic composite nonconvex optimization problem under standard assumptions.
SARAH: A novel method for machine learning problems using stochastic recursive gradient
L. M. Nguyen, J. Liu, K. Scheinberg, and M. Takáč · 2017
Earlier work this paper cites.
SPIDER: Near-optimal non-convex optimization via stochastic path integrated differential estimator
C. Fang, C. J. Li, Z. Lin, and T. Zhang · 2018
Earlier work this paper cites.
Lower bounds for non-convex stochastic optimization
Y. Arjevani, Y. Carmon, J. C. Duchi, D. J. Foster, N. Srebro, and B. Woodworth · 2019
Earlier work this paper cites.
Momentum-based variance reduction in non-convex SGD
A. Cutkosky and F. Orabona · 2019
Cited alongside, same era.
A hybrid stochastic optimization framework for stochastic composite nonconvex optimization
Q. Tran-Dinh, N. H. Pham, D. T. Phan, and L. M. Nguyen · 2019
Cited alongside, same era.
ProxSARAH: An efficient algorithmic framework for stochastic composite nonconvex optimization
H. N. Pham, M. L. Nguyen, T. D. Phan, and Q. Tran-Dinh · 2020
Closest in time.
Hybrid variance-reduced SGD algorithms for nonconvex-concave minimax problems
Q. Tran-Dinh, D. Liu, and L. M. Nguyen · 2020
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…