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

arXiv:2609.33240 · cs.LG, math.OC · Submitted 2026-09-27 · Read on arXiv

cs.LG, math.OC

Submitted: 2026-09-27

Updated: 2026-09-27

Comments: This paper is accepted by NeurIPS 2026

Code: https://github.com/Zhaoxian-Wu/ffa-theory

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

Terminology

• Accuracy — 35× in this paper · explained in 1 episode
• Benchmark — 13× in this paper · explained in 2 episodes
• Forward-Forward Algorithm — 13× in this paper
• Adam — 12× in this paper · explained in 2 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Predictive Coding — 9× in this paper · explained in 2 episodes
• Verification — 8× in this paper · explained in 2 episodes
• Perplexity — 6× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• In International Conference on Machine Learning — 5× in this paper
• Trace — 5× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Generalization — 4× in this paper · explained in 13 episodes
• Linear probe — 4× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Degeneracy — 3× in this paper · explained in 3 episodes
• Direct Feedback Alignment — 3× in this paper
• Failure Modes — 3× in this paper · explained in 3 episodes
• In International Conference on Learning Representations — 3× in this paper
• Objective Mismatch — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Continual Learning — 2× in this paper · explained in 2 episodes
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Data Augmentation — 2× in this paper · explained in 7 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Local Cross-Entropy — 2× in this paper
• Representation Learning — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Geometric Mismatch — 1× in this paper · explained in 2 episodes
• Local Optimization — 1× in this paper · explained in 2 episodes
• Lyapunov function — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Closed-Form Feedback-Free Learning with Forward Projection

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