BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
cs.LG, cond-mat.dis-nn, cs.AI
Submitted: 2025-12-03
Updated: 2026-02-17
Journal ref: Proceedings of the 14th International Conference on Learning Representations (ICLR 2026), pp. 25044-25061
Code: https://github.com/AI-Tech-Research-Lab/BEP
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Differentiable Weightless Neural Networks
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- XNOR-Net++: Improved Binary Neural Networks
- Adam: A Method for Stochastic Optimization
- CMA-ES for Hyperparameter Optimization of Deep Neural Networks
- Addition is All You Need for Energy-efficient Language Models
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks