5 papers · 1 filter
Non-monotone direct-search methods for deterministic and stochastic derivative-free optimization
Anjie Ding, Trang H. Tran, Luis Nunes Vicente
In derivative-free optimization (DFO), one minimizes functions for which the gradient is unavailable or expensive to compute. In many applications, objective function values and gr…
Stochastic block coordinate and function alternation for multi-objective optimization and learning
Trang H. Tran, Luis Nunes Vicente
Multi-objective optimization is central to many engineering and machine learning applications, where multiple objectives must be optimized in balance. While multi-gradient based op…
Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting
Duc Toan Nguyen, Trang H. Tran, Lam M. Nguyen
In this paper, we propose Adjusted Shuffling SARAH, a novel algorithm that integrates shuffling strategies into the recursive SARAH framework using a dynamic weighting mechanism to…
Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization
Quoc Tran-Dinh, Trang H. Tran, Lam M. Nguyen
This paper aims at developing novel shuffling gradient-based methods for tackling two classes of minimax problems: nonconvex-linear and nonconvex-strongly concave settings. The fir…
SMG: A Shuffling Gradient-Based Method with Momentum
Trang H. Tran, Lam M. Nguyen, Quoc Tran-Dinh
We combine two advanced ideas widely used in optimization for machine learning: shuffling strategy and momentum technique to develop a novel shuffling gradient-based method with mo…