mlsanityData to 14 Oct 2026

Nonlocal optimization of binary neural networks

arXiv 2204.01935 ↗First posted 5 Apr 2022cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph. We study the behaviour of this conversion in an under-parameterized BNN setting and propose stochastic versions of Belief Propagation (BP) and Survey Propagation (SP) message passing algorithms to overcome the intractability of their current formulation. Compared to traditional gradient methods for BNNs, our results indicate that both stochastic BP and SP find better configurations of the parameters in the BNN.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 24 references that are in the map. First posted on arXiv 5 Apr 2022.

Builds on

8 of 24 references.

References · 8

  1. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  2. 2017Bayesian Compression for Deep Learningcited by 116
  3. 2017Soft Weight-Sharing for Neural Network Compressioncited by 99
  4. 2013Loopy Belief Propagation for Approximate Inference: An Empirical Studycited by 76
  5. 2017Learning Discrete Weights Using the Local Reparameterization Trickcited by 29
  6. 2018Probabilistic Binary Neural Networkscited by 21
  7. 2014Revisiting Algebra and Complexity of Inference in Graphical Modelscited by 2
  8. 2014Relaxed Survey Propagation for The Weighted Maximum Satisfiability Problemcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Quadratic Unconstrained Binary Optimisation for Training and Regularisation of Binary Neural Networks
  2. 2023Compacting Binary Neural Networks by Sparse Kernel Selection
  3. 2022Sparsifying Binary Networks
  4. 2022Combinatorial optimization for low bit-width neural networks
  5. 2022Recurrent Bilinear Optimization for Binary Neural Networks
  6. 2021BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements
  7. 2025BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
  8. 2021AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks