Algorithms with Predictions

06/16/2020
by   Michael Mitzenmacher, et al.
0

We introduce algorithms that use predictions from machine learning applied to the input to circumvent worst-case analysis. We aim for algorithms that have near optimal performance when these predictions are good, but recover the prediction-less worst case behavior when the predictions have large errors.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2018

Beyond Worst-Case Analysis

In the worst-case analysis of algorithms, the overall performance of an ...
research
06/01/2020

Secretary and Online Matching Problems with Machine Learned Advice

The classical analysis of online algorithms, due to its worst-case natur...
research
02/28/2019

Optimal Algorithms for Ski Rental with Soft Machine-Learned Predictions

We consider a variant of the classic Ski Rental online algorithm with ap...
research
11/23/2020

Learnable and Instance-Robust Predictions for Online Matching, Flows and Load Balancing

This paper proposes a new model for augmenting algorithms with useful pr...
research
04/09/2020

Composable Sketches for Functions of Frequencies: Beyond the Worst Case

Recently there has been increased interest in using machine learning tec...
research
10/12/2021

Balancing Average and Worst-case Accuracy in Multitask Learning

When training and evaluating machine learning models on a large number o...
research
04/09/2022

The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization

Training with an emphasis on "hard-to-learn" components of the data has ...

Please sign up or login with your details

Forgot password? Click here to reset