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. 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.
The paper introduces the Shift‑Invariant Variance Estimator (SIVE) to remove same‑state noise from thermodynamic variance calculations in neural‑network training. SIVE provides an unbiased estimate of path variance without requiring Markov chain Monte Carlo stationarity, and it reveals a reproducible mid‑training trough and rebound in MNIST MLP trajectories that raw variance masks. Experiments across multiple localization scales confirm that SIVE captures a large portion of observation noise and satisfies an early‑drop/late‑rise criterion in most trajectory‑scale pairs.
arXiv:2610.27641v1 Announce Type: cross Abstract: Temperature scaling is typically applied as a post-hoc transformation of model probabilities. In posterior-induced flow language models, this creates...
arXiv:2605.16929v2 Announce Type: replace Abstract: Global climate models are essential tools to simulate past and potential future pathways of climate change, as well as associated climate impacts....
arXiv:2506. 19136v4 Announce Type: replace Abstract: We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules.
The paper introduces Langevin simulated bifurcation (LSB), a fast, parallel Boltzmann sampler that matches the accuracy of sequential MCMC methods. It also proposes conditional expectation matching (CEM), an efficient technique for estimating the effective temperature of samples from energy‑based models with conditional independence. Building on these, the authors develop sampler adaptive learning (SAL), which adjusts the model temperature to align with the distribution produced by LSB, enabling efficient training of semi‑restricted Boltzmann machines (SRBMs) and outperforming conventional methods on synthetic spin‑glass datasets.
The paper introduces IsingFormer, a Transformer model trained on long‑run MCMC configurations, which provides global proposal moves for Parallel Tempering (PT). By integrating these learned proposals into PT—forming Transformer‑Augmented Parallel Tempering (TAPT)—the authors demonstrate lower residual energies on 3D spin‑glass instances and improved efficiency on integer factorization tasks. A scaling study shows TAPT reduces the time‑to‑solution exponent by about 33% compared to standard PT across tested problem sizes.
NeuralBES is a differentiable emulator that blends a physics‑based resistance–capacitance thermal model with a shared neural encoder to predict building energy use. By mapping building metadata to physically bounded model coefficients, it solves a scalar linear recurrence in log‑space and uses a predictor–corrector loop to handle thermostat nonlinearity while maintaining full‑horizon gradient flow. Trained on the ResStock dataset, NeuralBES accurately models heterogeneous buildings across climate zones, achieving physics‑valid predictions with fewer parameters than transformer and recurrent baselines and outperforming grey‑box RC models in mean absolute percentage error.
arXiv:2608. 10941v1 Announce Type: new Abstract: Industrial time-series signals, such as turbine temperature and rotational speed in aero-engines, are essential for monitoring the health and operational status of complex dynamical systems.
arXiv:2611.06843v1 Announce Type: cross Abstract: Grain growth during heat treatment strongly affects the microstructure of polycrystalline materials and, consequently, their mechanical properties. A...
arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.