A Self-Attentive Meta-Optimizer with Group-Adaptive Learning Rates and Weight Decay

• URL: http://arxiv.org/abs/2605.04055v1
• Date: Fri, 10 Apr 2026 02:56:01 GMT
• Title: A Self-Attentive Meta-Optimizer with Group-Adaptive Learning Rates and Weight Decay
• Abstract summary: We propose a new modulation that integrates a self-attention mechanism to dynamically modulate per-group learning rates and weight decay.<n>To train the attention module, we introduce a meta-learning objective that combines gradient alignment, loss decrease, and gap.<n>A key novel contribution is the extension of homoscedastic uncertainty weighting (HUW) with task-specific priorities that directly scale the regularization terms.
• Score: 0.42970700836450487
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adaptive optimizers like AdamW apply uniform hyperparameters across all parameter groups, ignoring heterogeneous optimization dynamics across layers and modules. We address this limitation by proposing MetaAdamW - a new optimizer that integrates a self-attention mechanism to dynamically modulate per-group learning rates and weight decay. The modulation factors are produced by a lightweight Transformer encoder that operates on statistical features (gradient norms, momentum norms, correlations) extracted from each parameter group. To train the attention module, we introduce a meta-learning objective that combines gradient alignment, loss decrease, and generalization gap. A key novel contribution is the extension of homoscedastic uncertainty weighting (HUW) with task-specific priorities that directly scale the regularization terms - enabling domain knowledge to guide automatic loss balancing. Extensive experiments on five diverse tasks-time series forecasting (ETT), language modeling (WikiText-2), machine translation (Multi30k), image classification (CIFAR-10), and sentiment analysis (IMDB) - demonstrate that MetaAdamW consistently outperforms the standard AdamW baseline in terms of validation loss, accuracy, or perplexity. Depending on the task, MetaAdamW either reduces overall training time (by up to 17.11%) or improves performance (by up to 11.08%) while introducing only moderate overhead; in some cases, it can also mitigate issues of insufficient convergence caused by premature early stopping. Ablation studies validate the effectiveness of each component, including feature versions, grouping strategies, and the proposed priority-injected uncertainty weighting.

Related papers

• ISO: An RLVR-Native Optimization Stack [50.40395312897848]
  We operationalize spectral inheritance as Isospectral Optimization (ISO)<n>Offline, ISO-Merger combines the frame changes of shared-base specialists into a single fixed-spectrum model.<n>Online, ISO-Merger applies a chosen base, including AdamW and Muon, to the frame variables while keeping the base spectra fixed.
  arXiv  Detail & Related papers  (2026-07-21T17:51:36Z)
• Meta-Transfer Learning for mmWave Beam Alignment [8.956048958779315]
  MTL-BA is a meta-transfer learning framework for beam alignment in millimeter-wave multiple-input single-output (MISO) systems.<n>We show that MTL-BA matches the accuracy and spectral efficiency of full fine-tuning across various SNR levels.
  arXiv  Detail & Related papers  (2026-07-01T12:24:48Z)
• Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates [13.40796672049436]
  This paper proposes Ada2MS, an optimization algorithm that achieves a smooth transition between AdamW-like behavior and momentum-SGD-like behavior.<n>On the visual tasks evaluated in this study, Ada2MS obtains competitive results under a unified-comparison protocol.
  arXiv  Detail & Related papers  (2026-05-19T22:11:04Z)
• Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks [17.067788440109137]
  Mixture-of-Experts (MoE) models are now standard in state-of-the-art systems.<n>We investigate how MoE sparsity influences two distinct capability regimes: memorization skills and reasoning skills.
  arXiv  Detail & Related papers  (2025-08-26T04:31:28Z)
• Singular Value Decomposition on Kronecker Adaptation for Large Language Model [0.8747606955991707]
  Large pre-trained Transformer models achieve state-of-the-art results across diverse language and reasoning tasks.<n>Full fine-tuning incurs substantial storage, memory, and computational overhead.<n>We propose SoKA, a novel PEFT strategy that combines Kronecker-product tensor factorization with SVD-driven initialization and dynamic rank selection.
  arXiv  Detail & Related papers  (2025-06-18T08:28:53Z)
• Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence [131.41894248194995]
  We propose context-oriented decomposition adaptation (CorDA), a novel method that initializes adapters in a task-aware manner.<n>Thanks to the task awareness, our method enables two optional adaptation modes, knowledge-preserved mode (KPM) and instruction-previewed mode (IPM)
  arXiv  Detail & Related papers  (2025-06-16T07:55:14Z)
• Taming LLMs by Scaling Learning Rates with Gradient Grouping [49.91587150497186]
  Training large language models (LLMs) poses challenges due to their massive scale and heterogeneous architectures.<n>This work introduces Scaling with Gradient Grouping (SGG), an gradient wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling.
  arXiv  Detail & Related papers  (2025-06-01T15:30:37Z)
• Beyond Freezing: Sparse Tuning Enhances Plasticity in Continual Learning with Pre-Trained Models [10.904981532789824]
  Continual Learning with Pre-trained Models holds great promise for efficient adaptation across sequential tasks.<n>Existing approaches freeze PTMs and rely on auxiliary modules like prompts or adapters.<n>We propose Mutual Information-guided Sparse Tuning (MIST), a plug-and-play method that selectively updates a small subset of PTM parameters.
  arXiv  Detail & Related papers  (2025-05-26T13:09:25Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization [55.972018549438964]
  Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy.<n>We propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable fine-tuning of LLMs in heterogeneous environments.<n> Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.
  arXiv  Detail & Related papers  (2024-11-10T19:59:54Z)
• META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions [23.746620619512573]
  Recent work overcomes the effect of having to compute gradients of "megabatches" Work is widely used after update with competitive deep learning tasks.
  arXiv  Detail & Related papers  (2022-09-29T15:12:54Z)
• Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability [67.8426046908398]
  Generalizability and stability are two key objectives for operating reinforcement learning (RL) agents in the real world. This paper presents MetaPG, an evolutionary method for automated design of actor-critic loss functions.
  arXiv  Detail & Related papers  (2022-04-08T20:46:16Z)
• Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
  Variational autoencoders (VAE) are a powerful and widely-used class of generative models. We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
  arXiv  Detail & Related papers  (2021-01-06T17:36:26Z)

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.