Adaptive State-Dependent Diffusion for Derivative-Free Optimization
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Test-Time Anchoring for Discrete Diffusion Posterior Sampling
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 AnsweringGenerative Diffusion Model for Risk-Neutral Derivative Pricing
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
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
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 ExplanationSampling with Adaptive Variance for Multimodal Distributions
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…