SyncAI.news, a Varaisys broadcasting
Geometric Identification in Predict-Then-Optimize Learning
JX

Jiaxiao Xu, Changhong Mou, Keji Liu, Dinghua Xu, Yeyu Zhang

· 1 min read

ResearcharXiv cs.LG

Geometric Identification in Predict-Then-Optimize Learning

arXiv:2609.33472v1 Announce Type: new Abstract: Decision-focused surrogates can recover downstream decisions without identifying the quotient report. We characterize the equality set of the convex Smart Predict-then-Optimize surrogate (SPO+) population risk. Under central symmetry, the centered mean class is the unique Bayes minimizer exactly when every nonzero effective displacement makes the old optimizer leave the shifted optimal face with positive probability. This condition separates face crossing from selected-oracle disagreement and gives quantitative local coercivity. Without symmetry, strict crossing alone need not identify the mean; selection balance with reflected crossing restores quotient-report identification, and conditional versions extend the result to measurable predictors. These are population statements, without finite-sample report-recovery or generic transfer-regret guarantees. Closed-form mechanisms reproduce the analytic identities and rates. Portfolio, complete-matrix KuaiRec, and Energy/Storage studies measure predictive fidelity, shifted regret, and fitted-report geometry. A known data-generating process (DGP) companion retains their application geometries while isolating conditional-mean recovery and crossing, without testing the original observational assumptions.

Original source

This story was published by arXiv cs.LG and written by Jiaxiao Xu, Changhong Mou, Keji Liu, Dinghua Xu, Yeyu Zhang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News