SyncAI.news, a Varaisys broadcasting
Active Learning For Contextual Linear Optimization: A Margin-Based Approach
ML

Mo Liu, Paul Grigas, Heyuan Liu, Zuo-Jun Max Shen

· 1 min read

ResearcharXiv cs.LG

Active Learning For Contextual Linear Optimization: A Margin-Based Approach

arXiv:2305.06584v3 Announce Type: replace Abstract: We develop the first active learning method for contextual linear optimization. Specifically, we introduce a label acquisition algorithm that sequentially decides whether to request the ``labels'' of feature samples arriving in an unlabeled data stream, where the labels correspond to the objective coefficients in the linear optimization problem. The label acquisition rule is guided by the decision loss induced by the predicted coefficients, known as the Smart Predict-then-Optimize (SPO) loss. Motivated by the structure of the SPO loss, our algorithm uses the distance to degeneracy as a margin-based criterion for label acquisition. The algorithm processes incoming feature samples in batches, acquiring within each batch only the labels of samples whose distance to degeneracy falls below a rejection threshold. We derive non-asymptotic bounds for direct SPO-loss minimization over a general hypothesis class and for surrogate-loss minimization over a linear prediction class. These bounds demonstrate that, under certain natural conditions, our margin-based active learning algorithm requires fewer labels than supervised learning to achieve the same excess population risk for the chosen training loss. We provide concrete examples in which these conditions hold under continuous (sub-)Gaussian noise. Finally, we present numerical evidence demonstrating the practical value of our approach in applications such as personalized pricing and shortest-path problems.

Original source

This story was published by arXiv cs.LG and written by Mo Liu, Paul Grigas, Heyuan Liu, Zuo-Jun Max Shen. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News