L
Lam M. Nguyen
Researcher at IBM
Publications - 65
Citations - 1526
Lam M. Nguyen is an academic researcher from IBM. The author has contributed to research in topics: Convex function & Stochastic gradient descent. The author has an hindex of 15, co-authored 58 publications receiving 1063 citations. Previous affiliations of Lam M. Nguyen include McNeese State University & Lehigh University.
Papers
More filters
Proceedings Article
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
TL;DR: In this paper, the authors proposed a StochAstic Recursive Gradient Algorithm for finite-sum minimization (SARAH), which admits a simple recursive framework for updating stochastic gradient estimates.
Posted Content
SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
TL;DR: A StochAstic Recursive grAdient algoritHm (SARAH), as well as its practical variant SARAH+, as a novel approach to the finite-sum minimization problems is proposed, and a linear convergence rate is proven under strong convexity assumption.
Proceedings Article
SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
Lam M. Nguyen,Phuong Ha Nguyen,Marten van Dijk,Peter Richtárik,Katya Scheinberg,Martin Takáč +5 more
TL;DR: In this paper, a new analysis of convergence of SGD is performed under the assumption that stochastic gradients are bounded with respect to the true gradient norm, and they also propose an alternative convergence analysis for SGD with diminishing learning rate.
Posted Content
Stochastic Recursive Gradient Algorithm for Nonconvex Optimization
TL;DR: This paper studies and analyzes the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses and provides a sublinear convergence rate and a linear convergence rate for gradient dominated functions.
Posted Content
ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization
TL;DR: A new stochastic first-order algorithmic framework to solve stochastically composite nonconvex optimization problems that covers both finite-sum and expectation settings and new constant and adaptive step-sizes that help to achieve desired complexity bounds while improving practical performance are proposed.