3 papers
cs.LG2026
Variance-Optimal Control Variates for Learning with Black-box Feedback
Zihao Zhao, Shuhan Zhang, Kai Wang
Modern models increasingly learn through black-box oracles such as humans, optimization solvers, and external tools that provide feedback without exposing their internal mechanisms…
cs.LG2025
A Fully First-Order Layer for Differentiable Optimization
Zihao Zhao, Kai-Chia Mo, Shing-Hei Ho +2
Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems. However, computing gradients via implicit differentiation re…
cs.LG2025
Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimization
Zihao Zhao, Christopher Yeh, Lingkai Kong +1
Decision-focused learning (DFL) integrates predictive modeling and optimization by training predictors to optimize the downstream decision target rather than merely minimizing pred…