Decoupled Orthogonal Dynamics: Regularization for Deep Network Optimizers

• URL: http://arxiv.org/abs/2602.05136v1
• Date: Wed, 04 Feb 2026 23:41:51 GMT
• Title: Decoupled Orthogonal Dynamics: Regularization for Deep Network Optimizers
• Abstract summary: We argue that magnitude and direction play distinct roles and should be decoupled in dynamics.<n>We propose Orthogonal Dynamics Decoupling and instantiate it as AdamO: an SGD-style update handles the onedimensional norm control, while Adam's adaptive preconditioning is confined to the tangential subspace.<n> Experiments on vision and language tasks show that AdamO improves generalization and stability over AdamW without introducing additional complex constraints.
• Score: 7.170491058218013
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms to expand effective capacity while steering directions to learn features, whereas weight decay indiscriminately suppresses norm growth. This push--pull interaction induces radial oscillations, injecting noise into Adam's second-moment estimates and potentially degrading delicate tangential feature learning. We argue that magnitude and direction play distinct roles and should be decoupled in optimizer dynamics. We propose Orthogonal Dynamics Decoupling and instantiate it as AdamO: an SGD-style update handles the one-dimensional norm control, while Adam's adaptive preconditioning is confined to the tangential subspace. AdamO further incorporates curvature-adaptive radial step sizing and architecture-aware rules and projections for scale-invariant layers and low-dimensional parameters. Experiments on vision and language tasks show that AdamO improves generalization and stability over AdamW without introducing additional complex constraints.

Related papers

• Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors [110.10775872372047]
  We propose emphMagnitude-Direction-Direction (MD) Decoupling.<n>It factorizes each weight into a fixed-norm direction on a hypersphere and learnable per-row and per-column magnitude gains, updated at separate learning rates.<n>Across both Adam and Muon, MD Decoupling improves on well-tuned baselines, transfers the optimal LR across model width without retuning, and continues to help at scale on large Mixture-of-Experts models.
  arXiv  Detail & Related papers  (2026-06-24T15:40:26Z)
• Weibull Weight-Scale Parameter Evolution under AdamW Training Dynamics [0.0]
  We study why the Weibull weight-scale parameter $(t)$ grows, overshoots, and then relaxes during AdamW training.<n>Near saturation, alignment and decay approach balance, explaining the transition from weight-scale growth to relaxation.
  arXiv  Detail & Related papers  (2026-06-11T03:50:14Z)
• AdamO: A Collapse-Suppressed Optimizer for Offline RL [12.482937306811026]
  offline reinforcement learning can fail spectacularly when bootstrapped temporal-difference (TD) updates amplify their own errors, driving the critic toward extreme and unusable Q-values.<n>We model offline TD learning as a feedback system and analyze Adam-based critic updates.<n>We prove that this design theoretically guarantees worst-case task safety and preserves Adam's continuous-time dissipative dynamics.
  arXiv  Detail & Related papers  (2026-05-03T16:53:29Z)
• Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum [5.049533819651459]
  We propose a new and a diagonal extension, NAMO and NAMO-D, to provide the first principled integration of momentum with noise adaptation.<n> NAMO-D instead right-multiplies orthogonalized momentum by a diagonal matrix with clamped entries.<n>Experiments on pretraining GPT-2 models demonstrate improved performance of both NAMO and NAMO-D compared to the AdamW and Muon models.
  arXiv  Detail & Related papers  (2026-02-19T05:00:39Z)
• AdamHD: Decoupled Huber Decay Regularization for Language Model Pre-Training [0.2578242050187029]
  AdamHuberDecay is a drop-in replacement for AdamW that substitutes the $ell$ penalty with a decoupled smooth Huber regularizer.<n>Experiments on GPT-2 and GPT-3 pre-training demonstrate that AdamHuberDecay converges 10-15% faster in wall-clock time.
  arXiv  Detail & Related papers  (2025-11-18T18:08:20Z)
• Continuous-Time Analysis of Adaptive Optimization and Normalization [5.954511401622424]
  Adaptive optimization algorithms, particularly Adam and its variant AdamW, are fundamental components of modern deep learning.<n>This work presents a continuous-time formulation of Adam and AdamW, facilitating a tractable analysis of training dynamics.
  arXiv  Detail & Related papers  (2024-11-08T18:07:55Z)
• Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models [27.847140934456288]
  This paper proposes a new weight decay technique, Selective Projection Decay (SPD) SPD selectively imposes a strong penalty on certain layers while allowing others to change freely. When equipped with SPD, Adam consistently provides better in-distribution robustness and out-of-distribution performance on benchmarks.
  arXiv  Detail & Related papers  (2024-11-03T23:36:53Z)
• Robust Training of Neural Networks using Scale Invariant Architectures [70.67803417918854]
  In contrast to SGD, adaptive gradient methods like Adam allow robust training of modern deep networks. We show that this general approach is robust to rescaling of parameter and loss. We design a scale invariant version of BERT, called SIBERT, which when trained simply by vanilla SGD achieves performance comparable to BERT trained by adaptive methods like Adam.
  arXiv  Detail & Related papers  (2022-02-02T11:58:56Z)
• Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization [118.50301177912381]
  We show that Adam can converge to different solutions of the objective with provably different errors, even with weight decay globalization. We show that if convex, and the weight decay regularization is employed, any optimization algorithms including Adam will converge to the same solution.
  arXiv  Detail & Related papers  (2021-08-25T17:58:21Z)
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence [100.6913091147422]
  Existing rotated object detectors are mostly inherited from the horizontal detection paradigm. In this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology.
  arXiv  Detail & Related papers  (2021-06-03T14:29:19Z)
• Adam$^+$: A Stochastic Method with Adaptive Variance Reduction [56.051001950733315]
  Adam is a widely used optimization method for deep learning applications. We propose a new method named Adam$+$ (pronounced as Adam-plus) Our empirical studies on various deep learning tasks, including image classification, language modeling, and automatic speech recognition, demonstrate that Adam$+$ significantly outperforms Adam.
  arXiv  Detail & Related papers  (2020-11-24T09:28:53Z)
• MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients [112.00379151834242]
  We propose adaptive learning rate principle, in which the running mean of squared gradient in Adam is replaced by a weighted mean, with weights chosen to maximize the estimated variance each coordinate. This results in faster adaptation, which leads more desirable empirical convergence behaviors.
  arXiv  Detail & Related papers  (2020-06-21T21:47:43Z)
• AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights [53.8489656709356]
  Normalization techniques are a boon for modern deep learning. It is often overlooked, however, that the additional introduction of momentum results in a rapid reduction in effective step sizes for scale-invariant weights. In this paper, we verify that the widely-adopted combination of the two ingredients lead to the premature decay of effective step sizes and sub-optimal model performances.
  arXiv  Detail & Related papers  (2020-06-15T08:35:15Z)

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.