Skip to content
Preprint

Path-dependent Discrete Amortized Inference

Aug 2026 · 0 citations · 104 references
Computer Science

TL;DR

It is demonstrated that the Markovian assumption can both hamper signal propagation during training and catastrophically reduce the learned sampler's expressivity due to state aliasing.

Abstract

We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution. Notably, recent studies have shown that this problem can be efficiently solved by learning a deterministic Markov Decision Process (MDP) that progressively builds each object in proportion to the posterior. In this work, however, we demonstrate that the Markovian assumption can both hamper signal propagation during training and catastrophically reduce the learned sampler's expressivity due to state aliasing. To address these issues, we propose lifting the MDP with a learnable latent dynamical system that allows the underlying policy to depend on the entire past trajectory---and not only on the current state. In view of this, we refer to the resulting method as path-dependent discrete amortized inference. Importantly, we provably extend existing learning algorithms for discrete amortized samplers to our setting. In experiments on standard benchmark problems, we also show that our approach often leads to faster learning convergence and improved state space exploration relatively to prior techniques.

View source

Similar papers

Generative sequence modeling for infinite memory processes via predictive states

This work shows that the statistical complexity of the estimation problem is determined by the intrinsic dimension of the predictive state space, and establishes guarantees for an instantiation of the method based on deep neural network estimators, and supports these theoretical results with experiments.

Michael Wieck-Sosa, C. Shalizi · 1 citation

Scalable Diffusion SBI for Compositional Inference under Simulator Misspecification

Simulation-based inference is challenging when many heterogeneous observations must be composed, hierarchical latent structure must be preserved, and the simulator is misspecified relative to observed data. We develop sampling and fine-tuning methods for diffusion-based inference in design-conditional settings, where t...

Vincent D. Zaballa, Elliot E. Hui · 0 citations

High-Dimensional Simulation-Based Inference in Latent Spaces

This work describes the conditions under which latent-space inference recovers the desired target posterior and systematically study its empirical trade-offs, comparing latent and standard estimators while controlling for network capacity, regularization, optimization, and training compute.

L. Kühmichel, Stefan T. Radev, B. Koppolu et al. · 0 citations
#machine learning Preprint Sep 2026

Particle GFlowNets: Rethinking Generative Marginalization Models

This work describes an automatic criterion for full-state rejuvenation of the Gibbs sampler, derived from the Gelman-Rubin statistic, which plays a key role in speeding up learning convergence.

Tiago da Silva, Diego Mesquita, S. Lahlou · 0 citations
#artificial intelligence Preprint Oct 2026

Posterior sampling by source-space MCMC via prior-based few-step transport maps

This work develops a framework for source-space generalized Bayesian inference that combines inexpensive few-step prior transports with posterior stability guarantees and establishes Wasserstein error bounds between the exact and learned posteriors in terms of the joint population iMF and auxiliary-velocity loss.

Hoang Phuc Hau Luu, Marcelo Hartmann, Zhong-Jian Wang · 0 citations
#artificial intelligence Preprint Oct 2026

Discrete Wasserstein Flows for One-Step Generative Modeling

We introduce a new framework for one-step generative modelling on finite state spaces. To extend drifting beyond continuous domains, we use discrete Wasserstein geometry to define a target-relative KL gradient flow over the transitions of a reversible Markov kernel. We realize this probability flow at the particle leve...

Alessandro Micheli, Andrea Zerio, Samir Bhatt · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.