Differentiating Metropolis-Hastings to Optimize Intractable Densities
Övrigt konferensbidrag, 2023

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.

Metropolis-Hastings

Markov chain coupling

automatic differentiation

Författare

Gaurav Arya

Massachusetts Institute of Technology (MIT)

Ruben Seyer

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Göteborgs universitet

Frank Schäfer

Massachusetts Institute of Technology (MIT)

Kartik Chandra

Massachusetts Institute of Technology (MIT)

Alexander Lew

Massachusetts Institute of Technology (MIT)

Mathieu Huot

University of Oxford

Vikash Mansinghka

Massachusetts Institute of Technology (MIT)

Jonathan Ragan-Kelley

Massachusetts Institute of Technology (MIT)

Christopher Vincent Rackauckas

Massachusetts Institute of Technology (MIT)

JuliaHub, Inc.

Pumas-AI Inc.

Moritz Schauer

Göteborgs universitet

Chalmers, Matematiska vetenskaper, Tillämpad matematik och statistik

Differentiable Almost Everything Workshop of the 40th International Conference on Machine Learning
Honolulu, Hawaii, USA,

Ämneskategorier

Beräkningsmatematik

Transportteknik och logistik

Sannolikhetsteori och statistik

Fundament

Grundläggande vetenskaper

Mer information

Senast uppdaterat

2024-08-23