Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Generative Refinement for Low-Budget Black-Box Optimization
Edouard R. Dufour, Pascal Fua
Black-box optimization is a fundamental science and engineering tool that makes it possible to optimize objectives without gradient information. Unfortunately, as it often requires…
cs.LG2026
Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling
Hantao Zhang, Jieke Wu, Mingda Xu +3
For multivariate co-generation in scientific applications, we advocate pairwise block rather than joint modeling of all variables. This design mitigates the computational burden an…