arXiv上发表的多篇研究论文介绍了用于去中心化随机双层优化的新算法，解决了元学习和超参数优化等机器学习应用中的挑战。这些新方法旨在提高收敛速度并降低通信成本，尤其是在异构环境和重尾噪声条件下。其中一篇论文提出了无需强假设即可实现更快收敛的同步和交替更新策略，另一篇则介绍了一种对重尾噪声有效的归一化随机方差缩减双层梯度下降算法。第三篇论文侧重于实现非凸-强凸双层优化的近最优一阶预言机复杂度，第四篇则提出了一种基于惩罚的策略梯度方法，用于零和马尔可夫对策的鞍点上的双层优化，展示了具有竞争力的速率和性能。 AI
影响 双层优化算法的这些进展可以提高元学习和强化学习等复杂机器学习任务的效率和适用性。
排序理由 该集群包含多篇在arXiv上发表的学术论文，详细介绍了双层优化问题的新算法和理论分析。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2311.11342v5 Announce Type: replace Abstract: Stochastic bilevel optimization finds widespread applications in machine learning, including meta-learning, hyperparameter optimization, and neural architecture search. To extend stochastic bilevel optimization to distributed da…
arXiv:2509.15543v2 Announce Type: replace Abstract: Existing decentralized stochastic optimization methods assume the lower-level loss function is strongly convex and the stochastic gradient noise has finite variance. These strong assumptions typically are not satisfied in real-w…
arXiv:2306.14853v5 Announce Type: replace-cross Abstract: In this work, we consider bilevel optimization when the lower-level problem is strongly convex. Recent works show that with a Hessian-vector product (HVP) oracle, one can provably find an $\epsilon$-stationary point within…
arXiv:2605.26654v1 Announce Type: cross Abstract: Reinforcement learning (RL) often has a hierarchical structure, where an upper-level (UL) learner selects model parameters and a lower-level (LL) decision-making process responds, naturally leading to a bilevel optimization proble…
Reinforcement learning (RL) often has a hierarchical structure, where an upper-level (UL) learner selects model parameters and a lower-level (LL) decision-making process responds, naturally leading to a bilevel optimization problem. Most existing bilevel RL methods assume a singl…