{"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/large-scale-methods-for-distributionally","title":"Large-Scale Methods for Distributionally Robust Optimization","arxiv_id":"2010.05893","date":"2020-10-12","proceeding":"NeurIPS 2020 12","authors":["Daniel Levy","Yair Carmon","John C. Duchi","Aaron Sidford"],"abstract":"We propose and analyze algorithms for distributionally robust optimization of convex losses with conditional value at risk (CVaR) and $\\chi^2$ divergence uncertainty sets. We prove that our algorithms require a number of gradient evaluations independent of training set size and number of parameters, making them suitable for large-scale applications. For $\\chi^2$ uncertainty sets these are the first such guarantees in the literature, and for CVaR our guarantees scale linearly in the uncertainty level rather than quadratically as in previous work. We also provide lower bounds proving the worst-case optimality of our algorithms for CVaR and a penalized version of the $\\chi^2$ problem. Our primary technical contributions are novel bounds on the bias of batch robust risk estimation and the variance of a multilevel Monte Carlo gradient estimator due to [Blanchet & Glynn, 2015]. Experiments on MNIST and ImageNet confirm the theoretical scaling of our algorithms, which are 9--36 times more efficient than full-batch methods.","url_abs":"https://arxiv.org/abs/2010.05893v2","url_pdf":"https://arxiv.org/pdf/2010.05893v2.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":"large-scale-methods-for-distributionally","repo_url":"https://github.com/daniellevy/fast-dro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.05893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05893"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"deterministic:regex_extraction","url":"https://github.com/daniellevy/fast-dro","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"0267157a4a1ac6e6","entry":"chi_square_value","repo":"daniellevy/fast-dro","repo_kind":"official","path":"robust_losses.py","file_url":"https://github.com/daniellevy/fast-dro/blob/HEAD/robust_losses.py","link_basis":"first_harvest_node","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":"0267157a4a1ac6e6"}},{"code_sha256_prefix":"2b8de0efd0313a25","entry":"cvar_value","repo":"daniellevy/fast-dro","repo_kind":"official","path":"robust_losses.py","file_url":"https://github.com/daniellevy/fast-dro/blob/HEAD/robust_losses.py","link_basis":"first_harvest_node","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":"2b8de0efd0313a25"}},{"code_sha256_prefix":"ad7dd9787d3e8805","entry":"fenchel_kl_cvar","repo":"daniellevy/fast-dro","repo_kind":"official","path":"robust_losses.py","file_url":"https://github.com/daniellevy/fast-dro/blob/HEAD/robust_losses.py","link_basis":"first_harvest_node","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":"ad7dd9787d3e8805"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}