Tight dimension independent lower bound on the expected convergence rate for diminishing step sizes in sgd
- Phuong Ha Nguyen
- Lam Nguyen
- et al.
- 2019
- NeurIPS 2019
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
7 results for Marten van Dijk
Characterization of convex objective functions and optimal expected convergence rates for SGD
- Marten van Dijk
- Lam Nguyen
- et al.
- 2019
- ICML 2019
SGD and Hogwild! Convergence without the bounded gradients assumption
- Lam Nguyen
- Phuong Ha Nguyen
- et al.
- 2018
- ICML 2018
Besting the Black-Box: Barrier Zones for Adversarial Example Defense
- Kaleel Mahmood
- Phuong Ha Nguyen
- et al.
- 2021
- IEEE Access
Finite-sum smooth optimization with SARAH
- Lam M. Nguyen
- Marten van Dijk
- et al.
- 2022
- COAP
A unified convergence analysis for shuffling-type gradient methods
- Lam Nguyen
- Quoc Tran-Dinh
- et al.
- 2021
- JMLR
New convergence aspects of stochastic gradient algorithms
- Lam Nguyen
- Phuong Ha Nguyen
- et al.
- 2019
- JMLR