Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency
stat.ML, cs.LG
Submitted: 2026-05-27
Updated: 2026-11-07
Code: https://github.com/jackyzyb/sgprop
Terminology
Sources
- Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets
- The Forward-Forward Algorithm: Some Preliminary Investigations
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference