{"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/efficient-and-accurate-optimal-transport-with","title":"Efficient and Accurate Optimal Transport with Mirror Descent and Conjugate Gradients","arxiv_id":"2307.08507","date":"2023-07-17","proceeding":null,"authors":["Mete Kemertas","Allan D. Jepson","Amir-Massoud Farahmand"],"abstract":"We design a novel algorithm for optimal transport by drawing from the entropic optimal transport, mirror descent and conjugate gradients literatures. Our scalable and GPU parallelizable algorithm is able to compute the Wasserstein distance with extreme precision, reaching relative error rates of $10^{-8}$ without numerical stability issues. Empirically, the algorithm converges to high precision solutions more quickly in terms of wall-clock time than a variety of algorithms including log-domain stabilized Sinkhorn's Algorithm. We provide careful ablations with respect to algorithm and problem parameters, and present benchmarking over upsampled MNIST images, comparing to various recent algorithms over high-dimensional problems. The results suggest that our algorithm can be a useful addition to the practitioner's optimal transport toolkit.","url_abs":"https://arxiv.org/abs/2307.08507v2","url_pdf":"https://arxiv.org/pdf/2307.08507v2.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":"efficient-and-accurate-optimal-transport-with","repo_url":"https://github.com/adaptive-agents-lab/mdot-pncg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.08507","atlas_url":"https://app.syntology.ai/?focus=2307.08507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08507"}},"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/adaptive-agents-lab/mdot-pncg","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":10,"samples":[{"code_sha256_prefix":"7a24415cfcb9017b","entry":"dual_hessian","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/algorithmic.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/algorithmic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7a24415cfcb9017b"}},{"code_sha256_prefix":"88437d3c987de4f1","entry":"entropy","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/measurements.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/measurements.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88437d3c987de4f1"}},{"code_sha256_prefix":"bd5e1b0a2ccca13f","entry":"err_func","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/measurements.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/measurements.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd5e1b0a2ccca13f"}},{"code_sha256_prefix":"7e526be2d5a063be","entry":"eval_dual","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/algorithmic.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/algorithmic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e526be2d5a063be"}},{"code_sha256_prefix":"2328b4b281b9056d","entry":"kl_div","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/measurements.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/measurements.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2328b4b281b9056d"}},{"code_sha256_prefix":"42958997018c3581","entry":"make_dir","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/generic.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/generic.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42958997018c3581"}},{"code_sha256_prefix":"2956d3e6381ae672","entry":"round_altschuler","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/algorithmic.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/algorithmic.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2956d3e6381ae672"}},{"code_sha256_prefix":"cd0ecf3c7514d7ac","entry":"sample_distance_matrix","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/synth_data_generation.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/synth_data_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd0ecf3c7514d7ac"}},{"code_sha256_prefix":"77a4ee3f56121194","entry":"sample_uniform_from_simplex","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"utils/synth_data_generation.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/utils/synth_data_generation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77a4ee3f56121194"}},{"code_sha256_prefix":"1564dfe3c1ffac88","entry":"prepare_datasets","repo":"adaptive-agents-lab/mdot-pncg","repo_kind":"official","path":"mnist_experiments.py","file_url":"https://github.com/adaptive-agents-lab/mdot-pncg/blob/HEAD/mnist_experiments.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1564dfe3c1ffac88"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}