/

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

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

arXiv cs.LG · arxiv.org · 2026/05/07 13:00 · 11h ago

※ この記事の本文は近日中に AI が生成して差し替わります。現時点では上記サマリをご参照ください。

SourcearXiv cs.LGT2
Source Avg ★ 1.0
Type論文
Importance ★ 情報 (top 100% in Research)
Half-life 🏛️ 長期 (アーキテクチャ)
LangEN
Collected2026/05/07 22:00

元記事を読む

arxiv.org

本ページの本文・要約は AI による自動生成です。正確性は元記事 (arxiv.org) をご確認ください。

🔬 Research の他の記事もっと見る →

スカラー既約な学習ダイナミクスによる内生的レジームスイッチング

本論文は、外生ショックではなく学習ダイナミクス自体が内生的にレジーム転換を引き起こすメカニズムを提案する。スカラー既約性という条件下で、適応的学習が複数均衡間の遷移を生み、経済・金融時系列に見られる構造変化を説明できる可能性を示す。

Transformation Categorization Based on Group Decomposition Theory Using Parameter Division

arXiv:2605.04056v1 Announce Type: new Abstract: Representation learning seeks meaningful sensory representations without supervision and can model aspects of human development. Although many neural ne

Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search

arXiv:2605.04057v1 Announce Type: new Abstract: This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural knowledge while exploring new designs u

MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning

arXiv:2605.04058v1 Announce Type: new Abstract: Parameter-efficient transfer learning (PETL) has emerged as a pivotal paradigm for adapting pre-trained foundation models to downstream tasks, significa

Continual Distillation of Teachers from Different Domains

arXiv:2605.04059v1 Announce Type: new Abstract: Deep learning models continue to scale, with some requiring more storage than many large-scale datasets. Thus, we introduce a new paradigm: Continual Di

Lookahead Drifting Model

arXiv:2605.04060v1 Announce Type: new Abstract: Recently, a new paradigm named \emph{drifting model} has been proposed for mapping distributions, which achieves the SOTA image generation performance o

URL をコピーしました