Differentiating Metropolis-Hastings to Optimize Intractable Densities

Autor:	Arya, Gaurav, Seyer, Ruben, Schäfer, Frank, Chandra, Kartik, Lew, Alexander K., Huot, Mathieu, Mansinghka, Vikash K., Ragan-Kelley, Jonathan, Rackauckas, Christopher, Schauer, Moritz
Rok vydání:	2023
Předmět:	Statistics - Machine Learning Computer Science - Machine Learning Statistics - Computation Statistics - Methodology
Druh dokumentu:	Working Paper
Popis:	We develop an algorithm for automatic differentiation of Metropolis-Hastings samplers, allowing us to differentiate through probabilistic inference, even if the model has discrete components within it. Our approach fuses recent advances in stochastic automatic differentiation with traditional Markov chain coupling schemes, providing an unbiased and low-variance gradient estimator. This allows us to apply gradient-based optimization to objectives expressed as expectations over intractable target densities. We demonstrate our approach by finding an ambiguous observation in a Gaussian mixture model and by maximizing the specific heat in an Ising model. Comment: 6 pages, 6 figures; accepted at Differentiable Almost Everything Workshop of ICML 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.07961 Zobrazit plný text záznamu View this record from Arxiv