pith. sign in

arxiv: 2505.02222 · v4 · pith:HA5XVOEFnew · submitted 2025-05-04 · 💻 cs.LG · stat.ML

Practical Efficiency of Muon for Pretraining

classification 💻 cs.LG stat.ML
keywords muonadamwbatchdataefficiencyefficientsizeswhile
0
0 comments X
read the original abstract

We demonstrate that Muon, the simplest instantiation of a second-order optimizer, explicitly expands the Pareto frontier over AdamW on the compute-time tradeoff. We find that Muon is more effective than AdamW in retaining data efficiency at large batch sizes, far beyond the so-called critical batch size, while remaining computationally efficient, thus enabling more economical training. We study the combination of Muon and the maximal update parameterization (muP) for efficient hyperparameter transfer and present a simple telescoping algorithm that accounts for all sources of error in muP while introducing only a modest overhead in resources. We validate our findings through extensive experiments with model sizes up to four billion parameters and ablations on the data distribution and architecture.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds

    cs.LG 2026-05 unverdicted novelty 8.0

    SignSGD provably beats SGD by a factor of d under sparse noise via matched ℓ1-norm upper and lower bounds, with an equivalent result for Muon on matrices, and this predicts faster GPT-2 pretraining.

  2. Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective

    cs.LG 2026-06 unverdicted novelty 7.0

    Muon moves faster along signal river directions early but converges slower or oscillates near optima than GD due to orthogonal updates removing scale information, supporting two-stage optimization.

  3. OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality

    math.OC 2026-06 unverdicted novelty 7.0

    OptMuon combines orthogonalized momentum with closed-loop adaptation to achieve noise-adaptive convergence rates that automatically become near-optimal deterministic first-order rates without retuning when noise vanishes.

  4. Why Muon Outperforms Adam: A Curvature Perspective

    cs.LG 2026-06 conditional novelty 7.0

    Muon outperforms Adam by reducing curvature penalty via lower Normalized Directional Sharpness, as shown via Taylor approximation on LLM training and proven on stylized quadratic problems with heterogeneous curvature.

  5. Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers

    math.OC 2026-05 conditional novelty 7.0

    Proposes equivariant optimizers matched to the symmetry groups of embeddings, SwiGLU projections and MoE routers, with experiments showing consistent gains over AdamW on language model pre-training.

  6. Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters

    cs.LG 2026-05 unverdicted novelty 7.0

    Spectral clipping of leading singular values in gradient matrices stabilizes SGD for non-convex problems with heavy-tailed noise and achieves the optimal convergence rate O(K^{(2-2α)/(3α-2)}).

  7. Phases of Muon: When Muon Eclipses SignSGD

    math.OC 2026-05 unverdicted novelty 7.0

    On power-law covariance least squares problems, SignSVD (Muon) and SignSGD (Adam proxy) show three phases of relative performance depending on data exponent α and target exponent β.

  8. On the Convergence of Muon and Beyond

    cs.LG 2025-09 unverdicted novelty 7.0

    Muon-MVR2 attains the optimal anytime convergence rate of ~O(T^{-1/3}) in stochastic non-convex settings under horizon-free schedules.

  9. OptMuon: Closed-Loop Orthogonalized Momentum Methods for Stochastic Optimization with Zero-Noise Optimality

    math.OC 2026-06 unverdicted novelty 6.0

    OptMuon combines orthogonalized momentum with trajectory-dependent AdaGrad-Norm adaptation to obtain expected-stationarity rates of order T^{-1/2} + sigma^{1/2}T^{-1/4} or T^{-1/2} + sigma^{1/3}T^{-1/3} that reduce to...

  10. Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers

    math.OC 2026-05 unverdicted novelty 6.0

    Proposes equivariant optimizer updates matched to layer symmetries for embeddings, SwiGLU MLPs, and MoE routers, with reported gains in validation loss and training stability on several language model architectures.

  11. When is Warmstarting Effective for Scaling Language Models?

    cs.LG 2026-05 unverdicted novelty 6.0

    A 2x growth factor in model warmstarting yields reliable training speedups for language models under 20 tokens/parameter budgets, with an empirical upper bound on effective growth factors.

  12. MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration

    cs.LG 2026-03 unverdicted novelty 6.0

    MuonEq introduces pre-orthogonalization equilibration schemes that improve Muon optimizer performance during large language model pretraining.

  13. How to Allocate Your Tokens? Scaling Laws with Training Steps and Batch Size

    cs.LG 2026-07 unverdicted novelty 5.0

    Proposes a three-term scaling law for model size, training steps and batch size that recovers optimal batch size scaling and can be fitted using fewer runs by incorporating suboptimal batch sizes.

  14. Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?

    cs.LG 2026-06 unverdicted novelty 5.0

    The paper poses whether AdamW converges under heavy-tailed stochastic gradient noise and supplies a weighted-metric benchmark plus a corridor lower-bound showing how denominator memory can obscure large gradients.

  15. Muon Learns More Robust and Transferable Features than Adam

    cs.LG 2026-06 unverdicted novelty 5.0

    Muon learns more robust and transferable features than Adam and SGD, shown via corruption robustness tests, transfer experiments, layer-wise probes, effective rank measurements, and a theoretical proof on margins in a...

  16. Convergence of Spectral Descent for Non-smooth Optimization

    cs.LG 2026-05 unverdicted novelty 5.0

    Proves linear convergence of Spectral Descent (SD) and Truncated SD for non-smooth convex problems under stated conditions, sublinear rates for regularized versions via Frank-Wolfe, and recovery guarantees for robust ...

  17. Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered

    cs.LG 2026-05 unverdicted novelty 5.0

    Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.

  18. HTMuon: Improving Muon via Heavy-Tailed Spectral Correction

    cs.LG 2026-03 unverdicted novelty 5.0

    HTMuon modifies Muon to produce heavier-tailed updates and weight spectra via HT-SR theory, yielding up to 0.98 lower perplexity on LLaMA pretraining and serving as a plug-in for other Muon variants.

  19. Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training

    cs.LG 2025-09 unverdicted novelty 5.0

    Proposes low-rank orthogonalization and derives low-rank Muon and MSGD variants that outperform standard Muon on GPT-2 and LLaMA pretraining while providing iteration complexity bounds.

  20. Can Muon Fine-tune Adam-Pretrained Models?

    cs.LG 2026-05 unverdicted novelty 4.0

    Constraining fine-tuning updates with LoRA mitigates performance degradation when switching from Adam to Muon on pretrained models.