CORTEXA
← Browse
arxivcs.LG2026-07-11

Sharper Analysis of Single-Loop Methods for Bilevel Optimization

Yubo Zhou, Jun Shu, Luo Luo, Junmin Liu, Deyu Meng, Guang Dai, Haishan Ye

Bilevel optimization underpins many machine learning applications, including hyperparameter optimization, meta-learning, neural architecture search, and reinforcement learning. While hypergradient-based methods have advanced significantly, a gap persists between theoretical guarantees and practical single-loop implementations required for efficiency. We bridge this gap by establishing sharper convergence results for single-loop approximate implicit differentiation (AID) and iterative differentiation (ITD) methods, leveraging our proposed analytical framework, decoupled norm analysis (DNA). For AID, we improve the convergence rate from $\mathcal{O}(κ^6/K)$ to $\mathcal{O}(κ^5/K)$, where $κ$ is the condition number of the inner-level problem. For ITD, we prove that the asymptotic error is $\mathcal{O}(κ^2)$, exactly matching the known lower bound and improving upon the previous $\mathcal{O}(κ^3)$ guarantee. Numerical experiments on synthetic and real tasks corroborate our theoretical findings.

View free PDFSource page

Related papers

arxivmath.OCcs.LG2026-07-05

Unified convergence analysis for gradient descent optimization methods in the training of deep neural networks

Shokhrukh Ibragimov, Arnulf Jentzen

Gradient based optimization methods are nowadays the methods of choice for training deep neural networks (DNNs) in artificial intelligence (AI) systems. In practically relevant DNN training problems, one does usually not apply the standard gradient descent (GD) optimization metho…

View free PDFSource page
arxivcond-mat.mtrl-scics.LG2026-07-07

From Closed-Loop Optimization to Open Decision Making: Coupled Digital Twins for Predictive and Autonomous Microscopy

Yu Liu, Boris Slautin, Ian Mercer, Jon-Paul Maria, Sergei V. Kalinin

Automated experimentation is moving from closed-loop optimization toward open decision-making, where human or AI planners must forecast the consequences of candidate actions before executing them. Such forecasts require a model of both sides of the experiment: how the sample is l…

View free PDFSource page
arxivcs.LGcs.AI2026-07-08

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning

Zhenyu Hou, Yujiang Li, Jie Tang, Yuxiao Dong

Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs). Previous RL pipelines for LLMs were mostly synchronous and batch-interleaved, which is inefficient for long-horizon agentic tasks. Recently, asynchronous RL has emerged…

View free PDFSource page