{"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/algorithms-for-mean-field-variational","title":"Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space","arxiv_id":"2312.02849","date":"2023-12-05","proceeding":null,"authors":["Yiheng Jiang","Sinho Chewi","Aram-Alexandre Pooladian"],"abstract":"We develop a theory of finite-dimensional polyhedral subsets over the Wasserstein space and optimization of functionals over them via first-order methods. Our main application is to the problem of mean-field variational inference, which seeks to approximate a distribution $\\pi$ over $\\mathbb{R}^d$ by a product measure $\\pi^\\star$. When $\\pi$ is strongly log-concave and log-smooth, we provide (1) approximation rates certifying that $\\pi^\\star$ is close to the minimizer $\\pi^\\star_\\diamond$ of the KL divergence over a \\emph{polyhedral} set $\\mathcal{P}_\\diamond$, and (2) an algorithm for minimizing $\\text{KL}(\\cdot\\|\\pi)$ over $\\mathcal{P}_\\diamond$ based on accelerated gradient descent over $\\R^d$. As a byproduct of our analysis, we obtain the first end-to-end analysis for gradient-based algorithms for MFVI.","url_abs":"https://arxiv.org/abs/2312.02849v4","url_pdf":"https://arxiv.org/pdf/2312.02849v4.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":"algorithms-for-mean-field-variational","repo_url":"https://github.com/apooladian/mfvi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.02849","atlas_url":"https://app.syntology.ai/?focus=2312.02849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02849"}},"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/apooladian/mfvi","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11},"by_repo_kind":{"official":{"samples":11,"ran":11,"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":"987b4f5873f65d5b","entry":"V_Gaussian_highd","repo":"apooladian/mfvi","repo_kind":"official","path":"gaussian_utils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/gaussian_utils.py","link_basis":"first_harvest_node","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":"987b4f5873f65d5b"}},{"code_sha256_prefix":"b74a555b9f9adb40","entry":"V_logistic","repo":"apooladian/mfvi","repo_kind":"official","path":"BayesianUtils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/BayesianUtils.py","link_basis":"first_harvest_node","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":"b74a555b9f9adb40"}},{"code_sha256_prefix":"5a44c60d315c346b","entry":"build_M_FAST","repo":"apooladian/mfvi","repo_kind":"official","path":"misc_utils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/misc_utils.py","link_basis":"first_harvest_node","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":"5a44c60d315c346b"}},{"code_sha256_prefix":"0f34e9af21c91c24","entry":"compute_entropy_gradient_highd","repo":"apooladian/mfvi","repo_kind":"official","path":"optimization_utils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/optimization_utils.py","link_basis":"first_harvest_node","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":"0f34e9af21c91c24"}},{"code_sha256_prefix":"8139bf2df4a8f4ec","entry":"gaussian_int","repo":"apooladian/mfvi","repo_kind":"official","path":"misc_utils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/misc_utils.py","link_basis":"first_harvest_node","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":"8139bf2df4a8f4ec"}},{"code_sha256_prefix":"c4a97d909afb2eea","entry":"gaussian_x_int","repo":"apooladian/mfvi","repo_kind":"official","path":"misc_utils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/misc_utils.py","link_basis":"first_harvest_node","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":"c4a97d909afb2eea"}},{"code_sha256_prefix":"781f488f0dbe4f77","entry":"gradV_Gaussian_highd","repo":"apooladian/mfvi","repo_kind":"official","path":"gaussian_utils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/gaussian_utils.py","link_basis":"first_harvest_node","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":"781f488f0dbe4f77"}},{"code_sha256_prefix":"3c9084399513a9fe","entry":"gradV_logistic","repo":"apooladian/mfvi","repo_kind":"official","path":"BayesianUtils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/BayesianUtils.py","link_basis":"first_harvest_node","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":"3c9084399513a9fe"}},{"code_sha256_prefix":"af0e778af250e84c","entry":"langevin_monte_carlo","repo":"apooladian/mfvi","repo_kind":"official","path":"lmc_algorithm.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/lmc_algorithm.py","link_basis":"first_harvest_node","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":"af0e778af250e84c"}},{"code_sha256_prefix":"2c7490d7cda8093a","entry":"rho_gaussian_samples","repo":"apooladian/mfvi","repo_kind":"official","path":"gaussian_utils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/gaussian_utils.py","link_basis":"first_harvest_node","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":"2c7490d7cda8093a"}},{"code_sha256_prefix":"5ac707ebfd83b4ce","entry":"softmax","repo":"apooladian/mfvi","repo_kind":"official","path":"BayesianUtils.py","file_url":"https://github.com/apooladian/mfvi/blob/HEAD/BayesianUtils.py","link_basis":"first_harvest_node","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":"5ac707ebfd83b4ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}