paper-with-me

Papers

Sampler-Robust Optimization under Generative Models

2026-04-30 · Ziwei Zhang, Jonathan Yu-Meng Li arxiv

Modern stochastic optimization pipelines increasingly rely on learned generative models to represent uncertainty, while downstream decisions are evaluated almost entirely through Monte Carlo scenarios. This shifts the operational object of uncertainty from an explicit probability law to the sampler induced by the learned generator. Reliability therefore depends on two errors: sampler misspecification and finite-simulation error. We propose Sampler-Robust Optimization (SRO), which optimizes decisions against the worst-case sampler induced by perturbing the learned generator. This sampler-first formulation aligns with simulation-based decision pipelines and admits a sharpness-aware interpretation: it favors decisions whose performance is stable under generator perturbations, rather than merely under the nominal sampler. Under a coverage assumption, we show that the empirical worst-case objective provides a high-probability upper certificate for the true population objective, with finite-simulation error partially absorbed by the robustification used to guard against sampler misspecification. The framework accommodates generative models with or without explicit densities and admits efficient minimax procedures. Portfolio-optimization experiments show that SRO produces more stable decisions and improves out-of-sample performance under distribution shift.

📄 PDF Abstract BibTeX arXiv:2604.27447

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Generative Refinement for Low-Budget Black-Box Optimization

2026-07-01 · Edouard R. Dufour, Pascal Fua arxiv

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 many function evaluations, it can be ch…

Non-native Quantum Generative Optimization with Adversarial Autoencoders

2024-07-18 · Blake A. Wilson, Jonathan Wurtz, Vahagn Mkhitaryan, Michael Bezick 외

Large-scale optimization problems are prevalent in several fields, including engineering, finance, and logistics. However, most optimization problems cannot be efficiently encoded onto a physical system because the exist…

Fusing Neural and Physical: Augment Protein Conformation Sampling with Tractable Simulations

2024-02-16 · Jiarui Lu, Zuobai Zhang, Bozitao Zhong, Chence Shi 외

The protein dynamics are common and important for their biological functions and properties, the study of which usually involves time-consuming molecular dynamics (MD) simulations in silico. Recently, generative models h…

Physical Simulations

Generative Bayesian Optimization: Generative Models as Acquisition Functions

2025-10-29 · Rafael Oliveira, Daniel M. Steinberg, Edwin V. Bonilla arxiv

We present a general strategy for turning generative models into candidate solution samplers for batch Bayesian optimization (BO). The use of generative models for BO enables large batch scaling as generative sampling, o…

Multilevel Generative Samplers for Investigating Critical Phenomena

2025-03-11 · Ankur Singha, Elia Cellini, Kim A. Nicoli, Karl Jansen 외

Investigating critical phenomena or phase transitions is of high interest in physics and chemistry, for which Monte Carlo (MC) simulations, a crucial tool for numerically analyzing macroscopic properties of given systems…