arXiv:2512. 11415v3 Announce Type: replace-cross Abstract: We show that nonequilibrium dynamics can play a constructive role in unsupervised machine learning by inducing the spontaneous emergence of latent-state cycles.
arXiv:2607. 27077v1 Announce Type: new Abstract: Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability.
arXiv:2606. 30064v1 Announce Type: new Abstract: We introduce a data-driven probabilistic framework for learning systems based on Gibbs measures on hierarchical structures.
Energy-Based Models (EBMs) provide an interpretable framework for generative modeling of scientific data, but poor Markov Chain Monte Carlo mixing often limits their reliability. We introduce a training algorithm based on Parallel Trajectory Tempering (PTT), which exploits the continuity of the optimization path to maintain equilibrium sampling throughout learning.
arXiv:2607. 12922v1 Announce Type: cross Abstract: Stochastic-process models are, as a rule, far easier to simulate than to condition.
The paper studies when joint-embedding predictive architectures (JEPAs) can recover underlying causal states from high‑dimensional observations. It introduces a latent variable model where observations arise from causal states with action‑conditioned dynamics, and proposes an information‑theoretic objective that maximizes conditional likelihood while preserving state entropy. The authors prove identifiability conditions—particularly sufficient action‑induced variation—and instantiate the objective as an action‑modulated Gaussian additive‑noise model (A‑JEPA), demonstrating theoretical and empirical success in synthetic and visual benchmarks.
arXiv:2607. 25459v1 Announce Type: cross Abstract: Mechanistic interpretability has largely focused on language models and deterministic toy tasks.
The paper presents a probabilistic deep learning emulator—a ResNet‑inspired Conditional Variational Autoencoder—for the stochastic Holton–Mass model of stratospheric variability, which exhibits rare transitions between strong and weak polar vortex regimes. The emulator accurately reproduces short‑term dynamics, steady‑state distributions, regime persistence, rare transition rates, the committor function, and expected lead times. Analysis of the 32‑dimensional latent space via PCA reveals an unsupervised separation into four physically interpretable clusters that correspond to the two vortex regimes and their stable or transition‑prone states.
Stochastic-process models are, as a rule, far easier to simulate than to condition. Non-linear observations, non-Gaussian likelihoods, black-box information, and global constraints all induce intractable conditional laws, requiring bespoke, model-specific constructions.
FrOGS is a hybrid discrete neural sampler that couples an autoregressive model with a continuous-time Markov chain, trained under a single shared loss to sample alloy configurations across many chemical conditions. It produces independent, unbiased configurations, estimates the partition function, and yields consistent thermodynamic observables on a common absolute free‑energy scale. The method matches exact results for the 2D Ising model and reproduces reference phase diagrams for AgPd and CuAu, avoiding mode collapse and correctly recovering the stability range of the CuAu$_3$ phase.
We introduce a data-driven probabilistic framework for learning systems based on Gibbs measures on hierarchical structures. Unlike standard empirical risk minimization, where a dataset is used to identify a single optimal parameter, our approach transforms the empirical loss function into an interaction potential defining an energy-based model.
The paper presents a new one‑step generative modeling framework for finite state spaces, leveraging discrete Wasserstein geometry to define a target‑relative KL gradient flow over a reversible Markov kernel. The authors implement this flow at the particle level using Markov jumps and encode the resulting transport updates into a latent‑conditioned generator, enabling one‑step inference after training. Experiments on a controlled setting confirm KL dissipation, consistency between particle dynamics and probability flow, and accurate numerical scaling, while a finite‑capacity neural generator successfully tracks the exact transport targets.
arXiv:2606. 28854v1 Announce Type: cross Abstract: The common factor analytic model is related to Helmholtz and Boltzmann machines, can be conceived as a linear autoencoder, or can be thought of as a single-hidden-layer generative neural network.