arXiv:2310.04363v3 Announce Type: replace Abstract: Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits t...
arXiv:2608. 08644v1 Announce Type: new Abstract: We consider the problem of sampling compositional and discrete objects from a given unnormalized posterior distribution.
The paper introduces Amortized Factor Inference Networks (AFINs), a single inference network that can generalize across varying priors, likelihoods, latent dimensions, and observation counts. AFINs represent a model as a list of typed prior and likelihood factors and use an encode–merge–decode architecture to produce a Gaussian posterior approximation, with learned parameters independent of latent dimensionality or observation count. Experiments on synthetic and real datasets demonstrate that a single trained AFIN achieves competitive posterior approximations at significantly lower test‑time cost than NUTS and per‑task variational inference, with optional importance sampling further improving accuracy.
arXiv:2609.39525v1 Announce Type: new Abstract: Casting Bayesian inference as a neural network optimization problem targeting an amortized posterior is attractive, as it extends to otherwise intracta...
arXiv:2601. 07944v2 Announce Type: replace-cross Abstract: Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex, large-scale predictive problems.
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.
We develop a general method for amortized Bayesian inference on multilevel models of arbitrary structure. Given a generative model specified as a directed acyclic graph, our method automatically deriv...
The paper introduces a data‑free learning objective called relative trajectory balance for training diffusion models to sample from a posterior defined by a diffusion prior and an arbitrary black‑box constraint or likelihood. It proves asymptotic correctness of this objective and demonstrates its use across vision, language, and multimodal tasks, including classifier guidance, language infilling, and text‑to‑image generation. Additionally, the method is applied to continuous control with a score‑based behavior prior, achieving state‑of‑the‑art results in offline reinforcement learning.
The paper introduces Particle GFlowNets, showing that Generative Marginalization Models (MaMs) are equivalent to Generative Flow Networks. It extends MaMs to non‑autoregressive sampling and proposes an automatic full‑state rejuvenation criterion based on the Gelman‑Rubin statistic to accelerate learning. Experiments demonstrate significant training speedups in large combinatorial spaces.
arXiv:2610.18945v1 Announce Type: cross Abstract: Amortized Bayesian inference uses simulations to perform Bayesian estimation when likelihoods are expensive or analytically unavailable. However, lea...
arXiv:2609.40024v1 Announce Type: new Abstract: We develop a general method for amortized Bayesian inference on multilevel models of arbitrary structure. Given a generative model specified as a direc...
The paper investigates training diffusion models to sample from distributions defined by unnormalized densities or energy functions. It benchmarks various diffusion-structured inference techniques, including simulation-based variational methods and off-policy approaches such as continuous generative flow networks, highlighting their relative strengths and challenging some prior claims. Additionally, the authors introduce a new exploration strategy for off-policy methods that employs local search in the target space with a replay buffer, demonstrating improved sample quality across multiple target distributions.