A Probabilistic Framework for Learnable Optimization Algorithms

Abstract:We propose a statistical-learning framework for optimization algorithms. The framework is based on probability distributions over optimization trajectories induced by a distribution of optimization problems and a learnable optimization algorithm. Within this setting, optimization performance is represented through measurable performance functionals, including stopping times, contraction factors, and trajectory-level properties. The resulting framework provides a statistical perspective on optimization algorithms, allows their performance to be studied at the population level, and naturally accommodates the learning of optimization algorithms from data. Moreover, it enables the application of statistical-learning techniques to optimization, including PAC-Bayesian generalization guarantees for bounded optimization-specific performance measures. Experiments on convex, non-smooth, non-convex, and stochastic optimization problems illustrate the framework and demonstrate the statistical nature of optimization performance.

Machine Learning (cs.LG); Probability (math.PR)

arXiv:2408.11629 [cs.LG]

(or arXiv:2408.11629v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2408.11629 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.