paper-with-me

Papers

Data-Driven Performance Guarantees for Classical and Learned Optimizers

2024-04-22 · Rajiv Sambharya, Bartolomeo Stellato

We introduce a data-driven approach to analyze the performance of continuous optimization algorithms using generalization guarantees from statistical learning theory. We study classical and learned optimizers to solve families of parametric optimization problems. We build generalization guarantees for classical optimizers, using a sample convergence bound, and for learned optimizers, using the Probably Approximately Correct (PAC)-Bayes framework. To train learned optimizers, we use a gradient-based algorithm to directly minimize the PAC-Bayes upper bound. Numerical experiments in signal processing, control, and meta-learning showcase the ability of our framework to provide strong generalization guarantees for both classical and learned optimizers given a fixed budget of iterations. For classical optimizers, our bounds are much tighter than those that worst-case guarantees provide. For learned optimizers, our bounds outperform the empirical outcomes observed in their non-learned counterparts.

📄 PDF Abstract BibTeX arXiv:2404.13831

Code (1)

stellatogrp/datadrivenoptimizerguarantees 공식 구현 jax

Tasks

Learning TheoryMeta-Learning

Similar Papers 제목 키워드 기반

Learned reconstruction methods with convergence guarantees

2022-06-11 · Subhadip Mukherjee, Andreas Hauptmann, Ozan Öktem, Marcelo Pereyra 외

In recent years, deep learning has achieved remarkable empirical success for image reconstruction. This has catalyzed an ongoing quest for precise characterization of correctness and reliability of data-driven methods in…

Deep LearningImage ReconstructionSurvey

Data-Consistent Learning of Inverse Problems

2026-01-19 · Markus Haltmeier, Gyeongha Hwang arxiv

Inverse problems are inherently ill-posed, suffering from non-uniqueness and instability. Classical regularization methods provide mathematically well-founded solutions, ensuring stability and convergence, but often at t…

LLM-Evolved Pattern Generators for Optimal Classical Planning

2026-06-01 · Windy Phung, Dominik Drexler, Arnaud Lequen, Jendrik Seipp arxiv

Learned heuristics have recently become a competitive alternative to traditional domain-independent heuristics for satisficing planning. Existing approaches, however, focus on improving search guidance rather than guaran…

Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods

2020-03-10 · Daniel Otero Baguer, Johannes Leuschner, Maximilian Schmidt

In this work, we investigate the application of deep learning methods for computed tomography in the context of having a low-data regime. As motivation, we review some of the existing approaches and obtain quantitative r…

A Generalization Result for Convergence in Learning-to-Optimize

2024-10-10 · Michael Sucker, Peter Ochs

Learning-to-optimize leverages machine learning to accelerate optimization algorithms. While empirical results show tremendous improvements compared to classical optimization algorithms, theoretical guarantees are mostly…