{"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/improved-sampling-via-learned-diffusions","title":"Improved sampling via learned diffusions","arxiv_id":"2307.01198","date":"2023-07-03","proceeding":null,"authors":["Lorenz Richter","Julius Berner"],"abstract":"Recently, a series of papers proposed deep learning-based approaches to sample from target distributions using controlled diffusion processes, being trained only on the unnormalized target densities without access to samples. Building on previous work, we identify these approaches as special cases of a generalized Schr\\\"odinger bridge problem, seeking a stochastic evolution between a given prior distribution and the specified target. We further generalize this framework by introducing a variational formulation based on divergences between path space measures of time-reversed diffusion processes. This abstract perspective leads to practical losses that can be optimized by gradient-based algorithms and includes previous objectives as special cases. At the same time, it allows us to consider divergences other than the reverse Kullback-Leibler divergence that is known to suffer from mode collapse. In particular, we propose the so-called log-variance loss, which exhibits favorable numerical properties and leads to significantly improved performance across all considered approaches.","url_abs":"https://arxiv.org/abs/2307.01198v2","url_pdf":"https://arxiv.org/pdf/2307.01198v2.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":"improved-sampling-via-learned-diffusions","repo_url":"https://github.com/juliusberner/sde_sampler","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.01198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01198"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/juliusberner/sde_sampler","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":"27f52759b27497a3","entry":"filter_chirality","repo":"juliusberner/sde_sampler","repo_kind":"official","path":"sde_sampler/distr/aladip.py","file_url":"https://github.com/juliusberner/sde_sampler/blob/HEAD/sde_sampler/distr/aladip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27f52759b27497a3"}},{"code_sha256_prefix":"764abf0b944f41f9","entry":"get_bin_counts","repo":"juliusberner/sde_sampler","repo_kind":"official","path":"sde_sampler/distr/cox.py","file_url":"https://github.com/juliusberner/sde_sampler/blob/HEAD/sde_sampler/distr/cox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"764abf0b944f41f9"}},{"code_sha256_prefix":"8f7f43408f99e411","entry":"get_bin_vals","repo":"juliusberner/sde_sampler","repo_kind":"official","path":"sde_sampler/distr/cox.py","file_url":"https://github.com/juliusberner/sde_sampler/blob/HEAD/sde_sampler/distr/cox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f7f43408f99e411"}},{"code_sha256_prefix":"c2ecca936c640971","entry":"gmm_params","repo":"juliusberner/sde_sampler","repo_kind":"official","path":"sde_sampler/distr/gauss.py","file_url":"https://github.com/juliusberner/sde_sampler/blob/HEAD/sde_sampler/distr/gauss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2ecca936c640971"}},{"code_sha256_prefix":"67b6be2339aa44a8","entry":"read_points","repo":"juliusberner/sde_sampler","repo_kind":"official","path":"sde_sampler/distr/cox.py","file_url":"https://github.com/juliusberner/sde_sampler/blob/HEAD/sde_sampler/distr/cox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67b6be2339aa44a8"}},{"code_sha256_prefix":"e42f8b5d17e1bc8c","entry":"sample_uniform","repo":"juliusberner/sde_sampler","repo_kind":"official","path":"sde_sampler/distr/base.py","file_url":"https://github.com/juliusberner/sde_sampler/blob/HEAD/sde_sampler/distr/base.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e42f8b5d17e1bc8c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}