How much data is sufficient to learn high-performing algorithms?

08/08/2019
by   Maria-Florina Balcan, et al.
0

Algorithms for scientific analysis typically have tunable parameters that significantly influence computational efficiency and solution quality. If a parameter setting leads to strong algorithmic performance on average over a set of typical problem instances, that parameter setting---ideally---will perform well in the future. However, if the set of typical problem instances is small, average performance will not generalize to future performance. This raises the question: how large should this set be? We answer this question for any algorithm satisfying an easy-to-describe, ubiquitous property: its performance is a piecewise-structured function of its parameters. We are the first to provide a unified sample complexity framework for algorithm parameter configuration; prior research followed case-by-case analyses. We present applications from diverse domains, including biology, political science, and economics.

READ FULL TEXT
research
06/21/2020

Refined bounds for algorithm configuration: The knife-edge of dual class approximability

Automating algorithm configuration is growing increasingly necessary as ...
research
05/26/2019

Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees

Algorithms typically come with tunable parameters that have a considerab...
research
11/14/2020

Data-driven Algorithm Design

Data driven algorithm design is an important aspect of modern data scien...
research
12/24/2020

Generalization in portfolio-based algorithm selection

Portfolio-based algorithm selection has seen tremendous practical succes...
research
11/14/2016

Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems

Max-cut, clustering, and many other partitioning problems that are of si...
research
07/01/2020

Few-shots Parameter Tuning via Co-evolution

Generalization, i.e., the ability of addressing problem instances that a...
research
02/23/2023

Using Automated Algorithm Configuration for Parameter Control

Dynamic Algorithm Configuration (DAC) tackles the question of how to aut...

Please sign up or login with your details

Forgot password? Click here to reset