Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Hardware-Validated Benchmarking Study of Forward-Only Algorithms

arXiv:2511.01061 · cs.LG, cs.AI · Submitted 2025-11-02 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-11-02

Updated: 2026-10-12

Code: https://github.com/Przemyslaw11/BeyondBackpropagation

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Multi-Layer Perceptron — 1× in this paper

Sources

• Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations
• Mono-Forward: Revisiting Forward-Forward through Objective-Locality Decomposition
• The Forward-Forward Algorithm: Some Preliminary Investigations
• The Cascaded Forward Algorithm for Neural Network Training

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