QuadraSHAP: $ε$-Exact Shapley Values for Product Games in Logarithmic Parallel Time
We introduce QuadraSHAP, a method for $ε$-exact Shapley computation in product games, cooperative games whose coalition values factorize across players. Given a tolerance $ε\ge0$, the method determines a computational budget before evaluation, guaranteeing an absolute attribution error of at most $ε$ for every feature in exact arithmetic. By extending to weighted sums of product games, the framework supports baseline and empirical interventional attribution across a broad class of models, including log-link regression models, Cox proportional-hazards models, odds-scale classifiers, product-kernel machines, and tree-based models. For a $d$-player product game, we replace the exponentially ...
| Authors | Majid Mohammadi, Grigory Reznikov, Pavel Sinitcyn et al. |
|---|---|
| Primary category | cs.LG |
| Published | 7 May 2026 |
| Last updated at source | 25 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.