{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/optimal-budgeted-rejection-sampling-for","title":"Optimal Budgeted Rejection Sampling for Generative Models","arxiv_id":"2311.00460","date":"2023-11-01","proceeding":null,"authors":["Alexandre Verine","Muni Sreenivas Pydi","Benjamin Negrevergne","Yann Chevaleyre"],"abstract":"Rejection sampling methods have recently been proposed to improve the performance of discriminator-based generative models. However, these methods are only optimal under an unlimited sampling budget, and are usually applied to a generator trained independently of the rejection procedure. We first propose an Optimal Budgeted Rejection Sampling (OBRS) scheme that is provably optimal with respect to \\textit{any} $f$-divergence between the true distribution and the post-rejection distribution, for a given sampling budget. Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance. Through experiments and supporting theory, we show that the proposed methods are effective in significantly improving the quality and diversity of the samples.","url_abs":"https://arxiv.org/abs/2311.00460v2","url_pdf":"https://arxiv.org/pdf/2311.00460v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-celeba-64x64","task":"Image Generation","dataset":"CelebA 64x64","model":"BigGAN-OBRS","rank_in_archive_order":19,"of":39,"metrics":{"FID":"3.74","Precision":"0.74","Recall":"0.65"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-128x128","task":"Image Generation","dataset":"ImageNet 128x128","model":"BigGAN-OBRS","rank_in_archive_order":19,"of":23,"metrics":{"FID":"11.65","Precision":"0.27","Recall":"0.46"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}