The Drift Contract: Spectral Updates for Depth-Robust Local Learning
cs.LG
Submitted: 2026-09-16
Updated: 2026-09-16
Code: https://github.com/infinition/drift-contract
Terminology
Sources
- Old Optimizer, New Norm: An Anthology
- Scalable Optimization in the Modular Norm
- Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
- Muon is Scalable for LLM Training
- The Forward-Forward Algorithm: Some Preliminary Investigations
- Decoupled Greedy Learning of CNNs
- Training Neural Networks with Local Error Signals
- Muon in Vision Transformers: Optimizer-Recipe Interactions and Gradient Spectra
- Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation
- Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
- Muon is Not That Special: Random or Inverted Spectra Work Just as Well
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