The RNA-Binding Protein Zfp106 as a Therapeutic Target for Suppression of Amyotrophic Lateral Sclerosis
Abstract
Portfolio-based algorithm selection has seen tremendous practical success over the past two decades. This algorithm configuration procedure works by first selecting a portfolio of diverse algorithm parameter settings, and then, on a given problem instance, using an algorithm selector to choose a parameter setting from the portfolio with strong predicted performance. Oftentimes, both the portfolio and the algorithm selector are chosen using a training set of typical problem instances from the application domain at hand. In this paper, weprovide the first provable guarantees for portfolio-based algorithm selection. We analyze how large the training set should be to ensure that the resulting algorithm selectors average performance over the training set is close to its future (expected) performance. This involves analyzing three key reasons why these two quantities may diverge: 1) the learning theoretic complexity of the algorithm selector, 2) the sizeof the portfolio, and 3) the learning-theoretic complexity of the algorithms performance as a function of its parameters.We introduce an end-to-end learning-theoretic analysis of the portfolio construction and algorithm selection together. We prove that if the portfolio is large, overfitting is inevitable,even with an extremely simple algorithm selector. With experiments, we illustrate a tradeoff exposed by our theoretical analysis: as we increase the portfolio size, we can hope to include a well-suited parameter setting for every possible problem instance, but it becomes impossible to avoid overfitting.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 2023
- Accession Number
- AD1210807
Entities
People
- Brian L Black
Organizations
- University of California Regents