{"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/be-more-diverse-than-the-most-diverse-online","title":"Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms","arxiv_id":"2412.17622","date":"2024-12-23","proceeding":null,"authors":["Parham Rezaei","Farzan Farnia","Cheuk Ting Li"],"abstract":"The availability of multiple training algorithms and architectures for generative models requires a selection mechanism to form a single model over a group of well-trained generation models. The selection task is commonly addressed by identifying the model that maximizes an evaluation score based on the diversity and quality of the generated data. However, such a best-model identification approach overlooks the possibility that a mixture of available models can outperform each individual model. In this work, we numerically show that a mixture of generative models on benchmark image datasets can indeed achieve a better evaluation score (based on FID and KID scores), compared to the individual models. This observation motivates the development of efficient algorithms for selecting the optimal mixture of the models. To address this, we formulate a quadratic optimization problem to find an optimal mixture model achieving the maximum of kernel-based evaluation scores including kernel inception distance (KID) and R\\'enyi kernel entropy (RKE). To identify the optimal mixture of the models using the fewest possible sample queries, we view the selection task as a multi-armed bandit (MAB) problem and propose the Mixture Upper Confidence Bound (Mixture-UCB) algorithm that provably converges to the optimal mixture of the involved models. More broadly, the proposed Mixture-UCB can be extended to optimize every convex quadratic function of the mixture weights in a general MAB setting. We prove a regret bound for the Mixture-UCB algorithm and perform several numerical experiments to show the success of Mixture-UCB in finding the optimal mixture of text and image generative models. The project code is available at https://github.com/Rezaei-Parham/Mixture-UCB.","url_abs":"https://arxiv.org/abs/2412.17622v2","url_pdf":"https://arxiv.org/pdf/2412.17622v2.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":[{"paper_slug":"be-more-diverse-than-the-most-diverse-online","repo_url":"https://github.com/rezaei-parham/mixture-ucb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.17622","atlas_url":"https://app.syntology.ai/?focus=2412.17622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.17622"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rezaei-parham/mixture-ucb","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"259ec7338be8a457","entry":"compute_pairwise_distance","repo":"rezaei-parham/mixture-ucb","repo_kind":"official","path":"offline_mixture.py","file_url":"https://github.com/rezaei-parham/mixture-ucb/blob/HEAD/offline_mixture.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"259ec7338be8a457"}},{"code_sha256_prefix":"0e166911b5278ad1","entry":"compute_nearest_neighbour_distances","repo":"rezaei-parham/mixture-ucb","repo_kind":"official","path":"offline_mixture.py","file_url":"https://github.com/rezaei-parham/mixture-ucb/blob/HEAD/offline_mixture.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e166911b5278ad1"}},{"code_sha256_prefix":"547662aecde999ed","entry":"get_kth_value","repo":"rezaei-parham/mixture-ucb","repo_kind":"official","path":"online_reproducible.py","file_url":"https://github.com/rezaei-parham/mixture-ucb/blob/HEAD/online_reproducible.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"547662aecde999ed"}},{"code_sha256_prefix":"77070877f999ddf8","entry":"get_kth_value","repo":"rezaei-parham/mixture-ucb","repo_kind":"official","path":"offline_mixture.py","file_url":"https://github.com/rezaei-parham/mixture-ucb/blob/HEAD/offline_mixture.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77070877f999ddf8"}},{"code_sha256_prefix":"a408e16ed43950a5","entry":"compute_nearest_neighbour_distances","repo":"rezaei-parham/mixture-ucb","repo_kind":"official","path":"online_reproducible.py","file_url":"https://github.com/rezaei-parham/mixture-ucb/blob/HEAD/online_reproducible.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a408e16ed43950a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}