Extending $μ$P: Spectral Conditions for Feature Learning Across Optimizers

• URL: http://arxiv.org/abs/2602.20937v1
• Date: Tue, 24 Feb 2026 14:17:51 GMT
• Title: Extending $μ$P: Spectral Conditions for Feature Learning Across Optimizers
• Authors: Akshita Gupta, Marieme Ngom, Sam Foreman, Venkatram Vishwanath,
• Abstract summary: We propose a novel framework to derive $$P for a broader class of derivations, including AdamW, AD, LAMB, Sophia, Shampoo and Muon.<n>We implement our $$Ps on multiple benchmark models and demonstrate zero-shot learning rate transfer across increasing model width.
• Score: 3.5708391029226885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance of these optimization routines is highly sensitive to the choice of hyperparameters (HPs), which are computationally expensive to tune for large-scale models. Maximal update parameterization $(μ$P$)$ is a set of scaling rules which aims to make the optimal HPs independent of the model size, thereby allowing the HPs tuned on a smaller (computationally cheaper) model to be transferred to train a larger, target model. Despite promising results for SGD and Adam, deriving $μ$P for other optimizers is challenging because the underlying tensor programming approach is difficult to grasp. Building on recent work that introduced spectral conditions as an alternative to tensor programs, we propose a novel framework to derive $μ$P for a broader class of optimizers, including AdamW, ADOPT, LAMB, Sophia, Shampoo and Muon. We implement our $μ$P derivations on multiple benchmark models and demonstrate zero-shot learning rate transfer across increasing model width for the above optimizers. Further, we provide empirical insights into depth-scaling parameterization for these optimizers.

Related papers

• High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>We present textbfSMoA, a high-rank textbfStructured textbfMOdulation textbfAdapter that uses fewer trainable parameters while maintaining a higher rank.
  arXiv  Detail & Related papers  (2026-01-12T13:06:17Z)
• Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales [55.91454326946738]
  We study how the optimal learning rate and weight decay should scale with model width and depth for a wide range of languages.<n>We find that scaling the learning rate according to $$P improves transfer, but can still suffer from significant finite-width deviations.<n>For compute-optimal scaling, we find scaling independent weight decay as $1/mathrmwidth$ is nearly optimal across languages.
  arXiv  Detail & Related papers  (2025-12-05T11:03:41Z)
• POME: Post Optimization Model Edit via Muon-style Projection [74.73326657229347]
  Post-Optimization Model Edit (POME) enhances the performance of fine-tuned large language models.<n>It uses a muon-style projection to $Delta W$, the difference between the fine-tuned and pretrained weights.<n>As a simple post-processing step, POME is completely decoupled from the training pipeline.
  arXiv  Detail & Related papers  (2025-10-08T04:20:11Z)
• Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization [13.271737599933147]
  We introduce EntroPO, an entropy-enhanced framework that adapts existing preference optimization algorithms to the multi-turn, tool-assisted setting.<n>We validate EntroPO by fine-tuning a diverse suite of models from different families and sizes.<n>On the swebench leaderboard, our approach establishes new state-of-the-art results among open-weight models.
  arXiv  Detail & Related papers  (2025-09-15T20:36:19Z)
• Predictable Scale: Part I, Step Law -- Optimal Hyperparameter Scaling Law in Large Language Model Pretraining [59.369484219304866]
  We conduct an unprecedented empirical investigation training over 3,700 Large Language Models (LLMs) from scratch across 100 trillion tokens.<n>We establish a universal Scaling Law for hyperparameter optimization in LLM Pre-training, called Step Law.<n>Our estimated optima deviates from the global best performance found via exhaustive search by merely 0.094% on the test set.
  arXiv  Detail & Related papers  (2025-03-06T18:58:29Z)
• $f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization [54.94545757220999]
  $f$-PO is a novel framework that generalizes and extends existing approaches.<n>We conduct experiments on state-of-the-art language models using benchmark datasets.
  arXiv  Detail & Related papers  (2024-10-29T02:11:45Z)
• u-$μ$P: The Unit-Scaled Maximal Update Parametrization [4.275373946090221]
  We present a new scheme, u-$mu$P, which improves upon $mu$P by combining it with Unit Scaling.<n>The two techniques have a natural affinity: $mu$P ensures that the scale of activations is independent of model size, and Unit Scaling ensures that activations, weights and gradients begin training with a scale of one.
  arXiv  Detail & Related papers  (2024-07-24T17:58:42Z)
• Fine-Tuning Adaptive Stochastic Optimizers: Determining the Optimal Hyperparameter $ε$ via Gradient Magnitude Histogram Analysis [0.7366405857677226]
  We introduce a new framework based on the empirical probability density function of the loss's magnitude, termed the "gradient magnitude histogram" We propose a novel algorithm using gradient magnitude histograms to automatically estimate a refined and accurate search space for the optimal safeguard.
  arXiv  Detail & Related papers  (2023-11-20T04:34:19Z)
• VeLO: Training Versatile Learned Optimizers by Scaling Up [67.90237498659397]
  We leverage the same scaling approach behind the success of deep learning to learn versatiles. We train an ingest for deep learning which is itself a small neural network that ingests and outputs parameter updates. We open source our learned, meta-training code, the associated train test data, and an extensive benchmark suite with baselines at velo-code.io.
  arXiv  Detail & Related papers  (2022-11-17T18:39:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.