{"paper":{"title":"Selecting the Best in GANs Family: a Post Selection Inference Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Denny Wu, Ichiro Takeuchi, Kenji Fukumizu, Makoto Yamada, Ruslan Salakhutdinov, Yao-Hung Hubert Tsai","submitted_at":"2018-02-15T05:27:54Z","abstract_excerpt":"\"Which Generative Adversarial Networks (GANs) generates the most plausible images?\" has been a frequently asked question among researchers. To address this problem, we first propose an \\emph{incomplete} U-statistics estimate of maximum mean discrepancy $\\mathrm{MMD}_{inc}$ to measure the distribution discrepancy between generated and real images. $\\mathrm{MMD}_{inc}$ enjoys the advantages of asymptotic normality, computation efficiency, and model agnosticity. We then propose a GANs analysis framework to select and test the \"best\" member in GANs family using the Post Selection Inference (PSI) w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05411","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}