DeepAI AI Chat
Log In Sign Up

Algorithms with Prediction Portfolios

by   Michael Dinitz, et al.
University of California, Merced
Johns Hopkins University
Carnegie Mellon University
The University of Texas at Dallas

The research area of algorithms with predictions has seen recent success showing how to incorporate machine learning into algorithm design to improve performance when the predictions are correct, while retaining worst-case guarantees when they are not. Most previous work has assumed that the algorithm has access to a single predictor. However, in practice, there are many machine learning methods available, often with incomparable generalization guarantees, making it hard to pick a best method a priori. In this work we consider scenarios where multiple predictors are available to the algorithm and the question is how to best utilize them. Ideally, we would like the algorithm's performance to depend on the quality of the best predictor. However, utilizing more predictions comes with a cost, since we now have to identify which prediction is the best. We study the use of multiple predictors for a number of fundamental problems, including matching, load balancing, and non-clairvoyant scheduling, which have been well-studied in the single predictor setting. For each of these problems we introduce new algorithms that take advantage of multiple predictors, and prove bounds on the resulting performance.


page 1

page 2

page 3

page 4


Mixing predictions for online metric algorithms

A major technique in learning-augmented online algorithms is combining m...

Optimized conformal classification using gradient descent approximation

Conformal predictors are an important class of algorithms that allow pre...

Novel Techniques to Assess Predictive Systems and Reduce Their Alarm Burden

The performance of a binary classifier ("predictor") depends heavily upo...

Learning Predictions for Algorithms with Predictions

A burgeoning paradigm in algorithm design is the field of algorithms wit...

Learning structured approximations of operations research problems

The design of algorithms that leverage machine learning alongside combin...

Competition over data: how does data purchase affect users?

As machine learning (ML) is deployed by many competing service providers...

Robust Learning-Augmented Caching: An Experimental Study

Effective caching is crucial for the performance of modern-day computing...