Increasing Width Allows Greedy Layer-wise Training to Rival End-to-End Backpropagation in Self-Supervised Learning

arXiv:2610.00753 · cs.LG, cs.AI, cs.CV, cs.NE, q-bio.NC · Submitted 2026-09-30 · Read on arXiv

cs.LG, cs.AI, cs.CV, cs.NE, q-bio.NC

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Accuracy — 69× in this paper · explained in 1 episode
• Adam — 31× in this paper · explained in 2 episodes
• Loss Function — 13× in this paper · explained in 2 episodes
• Credit assignment — 8× in this paper · explained in 3 episodes
• Self-Supervised Learning — 8× in this paper · explained in 8 episodes
• Redundancy — 5× in this paper · explained in 2 episodes
• Generative AI — 4× in this paper · explained in 2 episodes
• Representation Learning — 4× in this paper · explained in 2 episodes
• Contrastive Learning — 3× in this paper · explained in 5 episodes
• Activation Function — 1× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 1× in this paper
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks