energy-based models 1equilibrium training 1generative modeling 1parallel trajectory tempering 1restricted boltzmann machines 1sampling methods 1
From the 1 of 3 linked papers with an AI index.
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
Nicolas Béreux, Aurélien Decelle, Cyril Furtlehner +1
The paper proposes Parallel Trajectory Tempering (PTT), a training method that keeps equilibrium sampling throughout learning of energy‑based models, enabling fast and stable train…
cs.LG2025★ 2 cited
Fast training and sampling of Restricted Boltzmann Machines
Nicolas Béreux, Aurélien Decelle, Cyril Furtlehner +2
Restricted Boltzmann Machines (RBMs) are powerful tools for modeling complex systems and extracting insights from data, but their training is hindered by the slow mixing of Markov…