PotentialEP: Backprop-Free Training of CIFAR-Scale Generative Models via Equilibrium Propagation

arXiv:2610.14409 · cs.LG, cs.ET, cs.NE · Submitted 2026-10-10 · Read on arXiv

cs.LG, cs.ET, cs.NE

Submitted: 2026-10-10

Updated: 2026-10-14

Comments: Under review at ICLR 2027. Code: github.com/alexgower/EnergyMatchingEqProp

Code: https://github.com/alexgower/EnergyMatchingEqProp

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes

Sources

• Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling
• Local Learning Rules for Out-of-Equilibrium Physical Generative Models
• Optical Generative Models
• Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks
• ePC: Fast and Deep Predictive Coding in Digital Simulation
• Training End-to-End Analog Neural Networks with Equilibrium Propagation
• Training a Predictive Coding Network on ImageNet using Equilibrium Propagation
• Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
• Flow Matching for Generative Modeling
• Training a Hopfield Variational Autoencoder with Equilibrium Propagation
• Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
• Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
• Improving and generalizing flow-based generative models with minibatch optimal transport
• Equilibrium Matching: Generative Modeling with Implicit Energy-Based Models
• Sample as You Infer: Predictive Coding With Langevin Dynamics

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks