Overview

Backpropagation uses the chain rule to send error signals from a model’s outputs backward through its layers, providing gradients for updating parameters. Work improves its efficiency and reach through memory-saving gradient methods, parallel scans, gradient approximations, and better scheduling, including for recurrent models and large language models. Alternatives such as feedback alignment, predictive coding, and forward-only local learning aim to reduce global backward communication or support biological and physical hardware. The central tension is that these alternatives may improve locality or memory use, but often struggle to match backpropagation’s accuracy, convergence, or measured end-to-end energy efficiency.

Latest papers

CardsList

48 papers6 papers in the last four weeks, up 20% on the four weeks before. 0.0% of all new papers.

  1. A method to automatically discover symbolic local learning rules

    Nov 9, 2026Andrea Perin, Fabio Anselmi, Stephane DenyLocal LearningBackpropagation

  2. Which Chains to Calibrate for Physical Backpropagation: Per-User Factors Versus Base-Station Chains

    Nov 2, 2026Xianzhong Li, Yuzhi Yang, Tianhao GuoWireless CommunicationsBackpropagation

  3. Neural LoFi with Backward Coupling: A Spectral Theory of Cross-Layer Feature Learning

    Oct 23, 2026Yatin Dandi, Matteo Vilucchio, Hugo Tabanelli +1Neural Network Training DynamicsBackpropagation

  4. FidLIF: Parallel Training of High-Fidelity Spiking Neurons with Exact BPTT

    Oct 12, 2026Kaixiang He, Yujie WuLIF NeuronsSpiking Neural Networks

  5. Connected Self Forcing: Beyond Local Learning in Video Autoregression

    Oct 8, 2026Dongbin Zhang, Chaoda Zheng, Kangjie Chen +13Autoregressive Video GenerationStreaming Video Generation

  6. Backward-State Policy Is Part of the Learning Algorithm

    Sep 30, 2026Shuxiao Xie, Shuyang Xie, Dezhi Ran +2Mixed-Precision QuantizationBackpropagation

  7. The Price of Locality: Why Forward-Forward Underperforms Backpropagation?

    Sep 27, 2026Zhaoxian Wu, Haichuan Liu, Tianyi ChenForward-Forward LearningNeural Network Optimization

  8. LocalProp: Neuro-Localized Memory-Efficient Backpropagation

    Sep 26, 2026Diana-Nicoleta Grigore, Iuliana Georgescu, Radu Tudor IonescuLocal LearningBackpropagation

  9. The Ups and Downs of Backprop Weights

    Sep 18, 2026Giuseppe Chindemi, Benjamin F. GreweModular Neural NetworksDynamic Neural Networks

  10. Wave Function Backpropagation with Explicit Temporal-Interval Dynamics

    Sep 1, 2026Byunggu Yu, Justin KimBackpropagationFeedforward Neural Networks

  11. The Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation

    Aug 20, 2026Hadi Al Mubasher, Mariette AwadCredit AssignmentNeural Network Training Dynamics

  12. Unifying Physical Backpropagation

    Aug 12, 2026Cyrill Bösch, Yigithan Gediz, Clara C. Wanjura +1On-Device Trainingadjoint method

  13. Learning in Deep Networks under Dale's Constraint

    Aug 7, 2026Roy Abel, Shimon UllmanBackpropagationBiologically Plausible Learning

  14. Reconstructing Backpropagation from Forward Fluctuations in Noise-modulated Neural Networks

    Jul 29, 2026Shuhei IkemotoBackpropagationNeuromorphic Computing

  15. Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform

    Jul 27, 2026Joel Siegert, Edoardo Ghignone, Michele MagnoBackpropagationContinual Robot Learning

  16. JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models

    Jul 20, 2026Ruiyi Ding, Jie Li, He Kang +3BackpropagationDiffusion Transformer

  17. Backpropagation-Free Trunk Training via the Split Forward Gradients

    Jul 18, 2026Tian Qin, Wei-Min HuangBackpropagationGradient Descent

  18. Backpropagation as a Nilpotent Linear System

    Jul 13, 2026Ahmed BoughammouraBackpropagationNeural Network Training Dynamics

  19. FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training

    Jun 22, 2026Dikshant Kukreja, Kritarth Prasad, Avinash Anand +6Automatic DifferentiationBackpropagation

  20. Automatic Differentiation from Scratch: How PyTorch Computes Gradients in Physics-Informed Neural Networks

    Jun 13, 2026Abdeladhim TahimiAutomatic DifferentiationBackpropagation

  21. Overcoming Rank Collapse in Feedback Alignment

    Jun 9, 2026Gauthier Boeshertz, Razvan Pascanu, Claudia ClopathBackpropagationNeural Network Optimization