{"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/delta-ai-local-objectives-for-amortized","title":"Delta-AI: Local objectives for amortized inference in sparse graphical models","arxiv_id":"2310.02423","date":"2023-10-03","proceeding":null,"authors":["Jean-Pierre Falet","Hae Beom Lee","Nikolay Malkin","Chen Sun","Dragos Secrieru","Thomas Jiralerspong","Dinghuai Zhang","Guillaume Lajoie","Yoshua Bengio"],"abstract":"We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs), which we call $\\Delta$-amortized inference ($\\Delta$-AI). Our approach is based on the observation that when the sampling of variables in a PGM is seen as a sequence of actions taken by an agent, sparsity of the PGM enables local credit assignment in the agent's policy learning objective. This yields a local constraint that can be turned into a local loss in the style of generative flow networks (GFlowNets) that enables off-policy training but avoids the need to instantiate all the random variables for each parameter update, thus speeding up training considerably. The $\\Delta$-AI objective matches the conditional distribution of a variable given its Markov blanket in a tractable learned sampler, which has the structure of a Bayesian network, with the same conditional distribution under the target PGM. As such, the trained sampler recovers marginals and conditional distributions of interest and enables inference of partial subsets of variables. We illustrate $\\Delta$-AI's effectiveness for sampling from synthetic PGMs and training latent variable models with sparse factor structure.","url_abs":"https://arxiv.org/abs/2310.02423v2","url_pdf":"https://arxiv.org/pdf/2310.02423v2.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":"delta-ai-local-objectives-for-amortized","repo_url":"https://github.com/gfnorg/delta-ai","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"pgm","method_name":"PGM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.02423","atlas_url":"https://app.syntology.ai/?focus=2310.02423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.02423"}},"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":"deterministic:regex_extraction","url":"https://github.com/GFNOrg/Delta-AI","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gfnorg/delta-ai","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":"b289c9e306fa90d2","entry":"get_ilist_and_set_dags","repo":"gfnorg/delta-ai","repo_kind":"official","path":"mnist/main_delta.py","file_url":"https://github.com/gfnorg/delta-ai/blob/HEAD/mnist/main_delta.py","link_basis":"first_harvest_node","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":"b289c9e306fa90d2"}},{"code_sha256_prefix":"41f18a3e1b770458","entry":"sleep","repo":"gfnorg/delta-ai","repo_kind":"official","path":"mnist/main_delta.py","file_url":"https://github.com/gfnorg/delta-ai/blob/HEAD/mnist/main_delta.py","link_basis":"first_harvest_node","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":"41f18a3e1b770458"}},{"code_sha256_prefix":"ce83daa38b7bd537","entry":"train_p","repo":"gfnorg/delta-ai","repo_kind":"official","path":"mnist/main_delta.py","file_url":"https://github.com/gfnorg/delta-ai/blob/HEAD/mnist/main_delta.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce83daa38b7bd537"}},{"code_sha256_prefix":"1005ab6934ffad36","entry":"load_mnist","repo":"GFNOrg/Delta-AI","repo_kind":"official","path":"mnist/data.py","file_url":"https://github.com/GFNOrg/Delta-AI/blob/HEAD/mnist/data.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":"1005ab6934ffad36"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}