paper-with-me

홈 › Papers

Adaptive State-Dependent Diffusion for Derivative-Free Optimization

2023-02-08 · Björn Engquist, Kui Ren, Yunan Yang

This paper develops and analyzes a stochastic derivative-free optimization strategy. A key feature is the state-dependent adaptive variance. We prove global convergence in probability with algebraic rate and give the quantitative results in numerical examples. A striking fact is that convergence is achieved without explicit information of the gradient and even without comparing different objective function values as in established methods such as the simplex method and simulated annealing. It can otherwise be compared to annealing with state-dependent temperature.

📄 PDF Abstract BibTeX arXiv:2302.04370

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Test-Time Anchoring for Discrete Diffusion Posterior Sampling

2025-10-02 · Litu Rout, Andreas Lugmayr, Yasamin Jafarian, Srivatsan Varadharajan 외 arxiv

While continuous diffusion models have achieved remarkable success, discrete diffusion offers a unified framework for jointly modeling text and images. Beyond unification, discrete diffusion provides faster inference, fi…

Question Answering

Generative Diffusion Model for Risk-Neutral Derivative Pricing

2026-03-21 · Nilay Tiwari arxiv

Denoising diffusion probabilistic models (DDPMs) have emerged as powerful generative models for complex distributions, yet their use in arbitrage-free derivative pricing remains largely unexplored. Financial asset prices…

Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors

2025-10-13 · Hongkai Zheng, Austin Wang, Zihui Wu, Zhengyu Huang 외 arxiv

Derivative-free Bayesian inversion arises in science and engineering applications, particularly when forward model is costly or infeasible to differentiate through. Existing derivative-free methods collapse the posterior…

Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI

2024-11-22 · CVPR 2025 1 · Won Jun Kim, Hyungjin Chung, JaeMin Kim, Sangmin Lee 외

Gradient-based methods are a prototypical family of explainability techniques, especially for image-based models. Nonetheless, they have several shortcomings in that they (1) require white-box access to models, (2) are v…

counterfactualCounterfactual Explanation

Sampling with Adaptive Variance for Multimodal Distributions

2024-11-20 · Björn Engquist, Kui Ren, Yunan Yang

We propose and analyze a class of adaptive sampling algorithms for multimodal distributions on a bounded domain, which share a structural resemblance to the classic overdamped Langevin dynamics. We first demonstrate that…