Can Representation Learning Decouple from Loss Minimization? Polar Updates Have an Answer
cs.LG, math.OC, stat.ML
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
- AMUSE: Anytime Muon with Stable Gradient Evaluation
- The large learning rate phase of deep learning: the catapult mechanism
- Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
- Training Deep Learning Models with Norm-Constrained LMOs
- Mechanism of feature learning in deep fully connected networks and kernel machines that recursively learn features
- Muon Learns More Robust and Transferable Features than Adam
- Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective
- Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
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