activity
20142022
most citedWeakly Coupled Dynamic Program: Information and Lagrangian Relaxations

3 citations · 4 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2022

Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

Tianyi Liu, Yan Li, Enlu Zhou +1

We investigate the role of noise in optimization algorithms for learning over-parameterized models. Specifically, we consider the recovery of a rank one matrix $Y^*\in R^{d\times d…

math.OC2022

Contextual Ranking and Selection with Gaussian Processes

Sait Cakmak, Siyang Gao, Enlu Zhou

In many real world problems, we are faced with the problem of selecting the best among a finite number of alternatives, where the best alternative is determined based on context sp…

math.OC2016

Solving the Dual Problems of Dynamic Programs via Regression

Helin Zhu, Fan Ye, Enlu Zhou

In recent years, information relaxation and duality in dynamic programs have been studied extensively, and the resulted primal-dual approach has become a powerful procedure in solv…

math.OC2016

Solving Multi-Objective Optimization via Adaptive Stochastic Search with Domination Measure

Joshua Q Hale, Helin Zhu, Enlu Zhou

For general multi-objective optimization problems, we propose a novel performance metric called domination measure to measure the quality of a solution, which can be intuitively in…

math.OC20161 cited

Simulation Optimization of Risk Measures with Adaptive Risk Levels

Helin Zhu, Joshua Hale, Enlu Zhou

Optimizing risk measures such as Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR) of a general loss distribution is usually difficult, because 1) the loss function might la…

math.OC20143 cited

Weakly Coupled Dynamic Program: Information and Lagrangian Relaxations

Fan Ye, Helin Zhu, Enlu Zhou

"Weakly coupled dynamic program" describes a broad class of stochastic optimization problems in which multiple controlled stochastic processes evolve independently but subject to a…