← Back to all news
arXiv Machine Learning

Learning to accelerate Krasnosel'skii-Mann fixed-point iterations with guarantees

The paper presents a learning-to-optimize (L2O) framework that injects summable perturbations into Krasnosel'skii-Mann iterations to accelerate solving fixed-point problems with nonexpansive mappings. It proves that, under metric sub-regularity, the parametrized iterations achieve local linear convergence with a vanishing bias and include all fast-converging iterations. The framework is applied to enhance operator splitting methods, such as Douglas‑Rachford, and is validated on a best‑approximation problem.

Related stories

arXiv Statistics ML
Oct 12

Provable Parameter-Free Fixed-Point Algorithms with Linear Convergence Rates

The paper introduces two parameter‑free Halpern fixed‑point algorithms that automatically exploit hidden contractivity without needing a prior estimate of the contraction factor. Both methods achieve explicit linear convergence rates for the fixed‑point residual and distance to the unique fixed point, with one variant using a line‑search to locally estimate the contraction factor. Extensions include parameter‑free Nesterov‑type variants and a Tikhonov‑regularized approach for cocoercive equations, yielding an iteration complexity of \(\mathcal{O}(\epsilon^{-1}\log(\epsilon^{-1}))\).

By Quoc Tran-Dinh, Pham Ngoc Anh, Ha Manh Tien
More like this →
arXiv Machine Learning
Sep 21

A regret minimization approach to fixed-point iterations

The paper introduces a conversion scheme that transforms regret-minimizing algorithms into fixed-point iterations, providing convergence guarantees derived from regret bounds. This framework generalizes the classical Krasnoselskii–Mann iterations, recovering them when applying Online Gradient Descent. By converting AdaGrad-based regret minimizers, the authors obtain new fixed-point iterations with adaptive guarantees, and numerical experiments show these AdaGrad-based iterations converge faster than traditional Krasnoselskii–Mann iterations.

By Joon Kwon
More like this →
Hugging Face Trending Papers
Sep 8

Sparse Data Augmentation for Optimization with Provable Guarantees

The paper investigates sparse data augmentation for nonconvex optimization in geometric machine learning. It shows that using a small, fixed sample of transformations—obtained before optimization—allows gradient descent to achieve an ε‑stationary point of the fully augmented objective with ≤ O((log|G|+log(1/δ))/ε²) transformation queries. This is more efficient than both full augmentation and standard group‑SGD, which require O(1/ε⁴) queries.

More like this →