arXiv Machine Learning

High-Dimensional Simulation-Based Inference in Latent Spaces

arXiv Machine Learning
Jun 5

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

arXiv:2603. 19312v3 Announce Type: replace Abstract: Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision to avoid representation collapse.

By Lucas Maes, Quentin Le Lidec, Damien Scieur, Yann LeCun, Randall Balestriero
arXiv Machine Learning
Sep 29

Mixed neural posterior estimation for simulators with discrete and continuous parameters

The paper extends Neural Posterior Estimation (NPE) to handle simulators whose parameter spaces contain both discrete and continuous dimensions. It introduces an inference network that factorizes the joint posterior into discrete and continuous components, using an autoregressive classifier for the discrete part and a generative model for the continuous part, trained jointly with a single simulation-based objective. A diagnostic tool for assessing calibration of the mixed posterior is also proposed, and the method is shown to produce accurate, calibrated posteriors on toy and real scientific simulators.

By Jan Boelts, Cornelius Schr\"oder, Jonas Beck, Jakob H. Macke, Michael Deistler, Daniel Gedon
arXiv AI
Oct 2

ProtoFlow: Prototype-Guided Flow Matching for Multivariate Time Series Forecasting

ProtoFlow is a new multivariate time series forecasting framework that combines vector‑quantized autoencoding with prototype‑guided flow matching. It maps sequences into a discrete latent space, constructs a structured prior from the learned VQ codebook, and trains a DiT‑based rectified flow to transport samples from this prior to future latent representations conditioned on past observations. By replacing generic Gaussian noise with a learned prototype prior, ProtoFlow eliminates autoregressive rollout mismatch and achieves faster training convergence while delivering superior forecasting performance on benchmark datasets.

By Shibo Feng, Wanjin Feng, Yang Qiu, Deheng Ye, Peilin Zhao, Chunyan Miao
arXiv Statistics ML
Sep 21

Neural composite likelihood estimation: simulation based inference for time series

Neural Composite Likelihood Estimation (NCLE) extends simulation‑based inference to high‑dimensional time series by partitioning long sequences into equal‑sized batches. For each batch, a neural network estimates the likelihood via conditional density estimation, and the product of these batch likelihoods forms an approximate composite likelihood. Frequentist inference is then performed by maximizing this composite likelihood to obtain a point estimate and by estimating the Godambe information matrix to derive confidence intervals.

By Grace Yan, Mark Beaumont, Dennis Prangle
arXiv Machine Learning
Oct 28

Adapting Neural Posterior Estimators for Simulation-Based Inference in Agent-Based Models

The paper presents a framework called SNPE‑TTT for adapting pre‑trained neural posterior estimators, specifically conditional normalizing flows, to new inference tasks in agent‑based models (ABMs). It explores four adaptation strategies—full‑parameter adaptation, low‑rank adaptation, and two gradient‑based update spaces—and evaluates them on economic simulation models with both tractable and intractable likelihoods. Results show that the framework can improve posterior recovery with a limited number of target simulations, though performance varies by task and adaptation method.

By Junyao Zhang, Jinglai Li, Junqi Tang