Fast Rates for Contextual Linear Optimization

by   Yichun Hu, et al.

Incorporating side observations of predictive features can help reduce uncertainty in operational decision making, but it also requires we tackle a potentially complex predictive relationship. Although one may use a variety of off-the-shelf machine learning methods to learn a predictive model and then plug it into our decision-making problem, a variety of recent work has instead advocated integrating estimation and optimization by taking into consideration downstream decision performance. Surprisingly, in the case of contextual linear optimization, we show that the naive plug-in approach actually achieves regret convergence rates that are significantly faster than the best-possible by methods that directly optimize down-stream decision performance. We show this by leveraging the fact that specific problem instances do not have arbitrarily bad near-degeneracy. While there are other pros and cons to consider as we discuss, our results highlight a very nuanced landscape for the enterprise to integrate estimation and optimization.



There are no comments yet.


page 1

page 2

page 3

page 4


When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making

As machine learning (ML) models are increasingly being employed to assis...

Automating Predictive Modeling Process using Reinforcement Learning

Building a good predictive model requires an array of activities such as...

Careful! Training Relevance is Real

There is a recent proliferation of research on the integration of machin...

Implications of Human Irrationality for Reinforcement Learning

Recent work in the behavioural sciences has begun to overturn the long-h...

Bootstrap Robust Prescriptive Analytics

We address the problem of prescribing an optimal decision in a framework...

Forming Predictive Features of Tweets for Decision-Making Support

The article describes the approaches for forming different predictive fe...

Machine Learning with Operational Costs

This work proposes a way to align statistical modeling with decision mak...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.