{"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/a-theory-for-conditional-generative-modeling","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources","arxiv_id":"2502.14583","date":"2025-02-20","proceeding":null,"authors":["Rongzhen Wang","Yan Zhang","Chenyu Zheng","Chongxuan Li","Guoqiang Wu"],"abstract":"The success of large generative models has driven a paradigm shift, leveraging massive multi-source data to enhance model capabilities. However, the interaction among these sources remains theoretically underexplored. This paper takes the first step toward a rigorous analysis of multi-source training in conditional generative modeling, where each condition represents a distinct data source. Specifically, we establish a general distribution estimation error bound in average total variation distance for conditional maximum likelihood estimation based on the bracketing number. Our result shows that when source distributions share certain similarities and the model is expressive enough, multi-source training guarantees a sharper bound than single-source training. We further instantiate the general theory on conditional Gaussian estimation and deep generative models including autoregressive and flexible energy-based models, by characterizing their bracketing numbers. The results highlight that the number of sources and similarity among source distributions improve the advantage of multi-source training. Simulations and real-world experiments validate our theory. Code is available at: \\url{https://github.com/ML-GSAI/Multi-Source-GM}.","url_abs":"https://arxiv.org/abs/2502.14583v1","url_pdf":"https://arxiv.org/pdf/2502.14583v1.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":"a-theory-for-conditional-generative-modeling","repo_url":"https://github.com/ml-gsai/multi-source-gm","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/2502.14583","atlas_url":"https://app.syntology.ai/?focus=2502.14583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14583"}},"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/ml-gsai/multi-source-gm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"ran_draft_wrong":2,"ran_honours":2},"by_repo_kind":{"official":{"samples":13,"ran":13,"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":"73e67952514d4636","entry":"calculate_empirical_TV","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"simulations/util.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/simulations/util.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":"73e67952514d4636"}},{"code_sha256_prefix":"a14db9805bf41197","entry":"edm_sampler","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/generate_images.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/generate_images.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a14db9805bf41197"}},{"code_sha256_prefix":"a2b45afa097b55b6","entry":"file_ext","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/dataset_tool.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/dataset_tool.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2b45afa097b55b6"}},{"code_sha256_prefix":"863886ae28872158","entry":"format_time","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/dnnlib/util.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/dnnlib/util.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":"863886ae28872158"}},{"code_sha256_prefix":"cf4282fe49551c8c","entry":"format_time_brief","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/dnnlib/util.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/dnnlib/util.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":"cf4282fe49551c8c"}},{"code_sha256_prefix":"d011780cb7c4038f","entry":"generate_shared_means","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"simulations/run_gaussian.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/simulations/run_gaussian.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":"d011780cb7c4038f"}},{"code_sha256_prefix":"dd1dc700e87f36cc","entry":"maybe_min","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/dataset_tool.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/dataset_tool.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd1dc700e87f36cc"}},{"code_sha256_prefix":"49d89884be5dc515","entry":"mp_silu","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/training/networks_edm2.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/training/networks_edm2.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":"49d89884be5dc515"}},{"code_sha256_prefix":"ebfd171dc25ba0ce","entry":"normalize","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/training/networks_edm2.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/training/networks_edm2.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":"ebfd171dc25ba0ce"}},{"code_sha256_prefix":"cacd4f6ec202d9b4","entry":"parse_int_list","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/generate_images.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/generate_images.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cacd4f6ec202d9b4"}},{"code_sha256_prefix":"fcf68d736821de45","entry":"parse_nimg","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/train_edm2.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/train_edm2.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":"fcf68d736821de45"}},{"code_sha256_prefix":"07b21b35ecb4815c","entry":"parse_tuple","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/dataset_tool.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/dataset_tool.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":"07b21b35ecb4815c"}},{"code_sha256_prefix":"d0955d86500b69a3","entry":"tuple_product","repo":"ml-gsai/multi-source-gm","repo_kind":"official","path":"real_world_experiments/dnnlib/util.py","file_url":"https://github.com/ml-gsai/multi-source-gm/blob/HEAD/real_world_experiments/dnnlib/util.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":"d0955d86500b69a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}