6 papers
Proximity operator characterization for abstract convex functions
Ewa Bednarczuk, The Hung Tran
We consider proximity operator as a selector of the subgradient in the context of abstract convexity and characterize its properties in term of minimization problems. We also inves…
Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks
Azza Fadhel, The Hung Tran, Trong Nghia Hoang +1
We consider the problem of offline black-box optimization, where the goal is to discover optimal designs (e.g., molecules or materials) from past experimental data. A key challenge…
Primal-Dual algorithms for Abstract convex functions with respect to quadratic functions
Ewa Bednarczuk, The Hung Tran
We consider the saddle point problem where the objective functions are abstract convex with respect to the class of quadratic functions. We propose primal-dual algorithms using the…
ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge
Manh Cuong Dao, The Hung Tran, Phi Le Nguyen +2
This paper studies the black-box optimization task which aims to find the maxima of a black-box function using a static set of its observed input-output pairs. This is often achiev…
High-Dimensional Bayesian Optimization via Random Projection of Manifold Subspaces
Quoc-Anh Hoang Nguyen, The Hung Tran
Bayesian Optimization (BO) is a popular approach to optimizing expensive-to-evaluate black-box functions. Despite the success of BO, its performance may decrease exponentially as t…
Primal-dual algorithm for weakly convex functions under sharpness conditions
Ewa Bednarczuk, The Hung Tran, Monika Syga
We investigate the convergence of the primal-dual algorithm for composite optimization problems when the objective functions are weakly convex. We introduce a modified duality gap…