DeepAI AI Chat
Log In Sign Up

On Sampling with Approximate Transport Maps

by   Louis Grenioux, et al.

Transport maps can ease the sampling of distributions with non-trivial geometries by transforming them into distributions that are easier to handle. The potential of this approach has risen with the development of Normalizing Flows (NF) which are maps parameterized with deep neural networks trained to push a reference distribution towards a target. NF-enhanced samplers recently proposed blend (Markov chain) Monte Carlo methods with either (i) proposal draws from the flow or (ii) a flow-based reparametrization. In both cases, the quality of the learned transport conditions performance. The present work clarifies for the first time the relative strengths and weaknesses of these two approaches. Our study concludes that multimodal targets can reliability be handled with flow-based proposals up to moderately high dimensions. In contrast, methods relying on reparametrization struggle with multimodality but are more robust otherwise in high-dimensional settings and under poor training. To further illustrate the influence of target-proposal adequacy, we also derive a new quantitative bound for the mixing time of the Independent Metropolis-Hastings sampler.


page 15

page 17


Annealed Flow Transport Monte Carlo

Annealed Importance Sampling (AIS) and its Sequential Monte Carlo (SMC) ...

LSB: Local Self-Balancing MCMC in Discrete Spaces

Markov Chain Monte Carlo (MCMC) methods are promising solutions to sampl...

Efficient Multimodal Sampling via Tempered Distribution Flow

Sampling from high-dimensional distributions is a fundamental problem in...

Machine Learning Trivializing Maps: A First Step Towards Understanding How Flow-Based Samplers Scale Up

A trivializing map is a field transformation whose Jacobian determinant ...

Transport Reversible Jump Proposals

Reversible jump Markov chain Monte Carlo (RJMCMC) proposals that achieve...

Transport Elliptical Slice Sampling

We introduce a new framework for efficient sampling from complex probabi...

Normalizing flow sampling with Langevin dynamics in the latent space

Normalizing flows (NF) use a continuous generator to map a simple latent...