{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FPVNOD2AJTVXXQCJADWWHBORZJ","short_pith_number":"pith:FPVNOD2A","canonical_record":{"source":{"id":"1802.08089","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-22T15:06:51Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.ML"],"title_canon_sha256":"315779882f6816cebb967be56d625bd6d027e8bd41564a94f79bbad9962763e8","abstract_canon_sha256":"51d91227111aa8fcf89a763ee3975cbe0429a116824d34cd513dd9543ffe8750"},"schema_version":"1.0"},"canonical_sha256":"2bead70f404ceb7bc04900ed6385d1ca68d677223ab46f7797facfcd1c8d5fb8","source":{"kind":"arxiv","id":"1802.08089","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08089","created_at":"2026-05-18T00:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08089v2","created_at":"2026-05-18T00:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08089","created_at":"2026-05-18T00:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"FPVNOD2AJTVX","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FPVNOD2AJTVXXQCJ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FPVNOD2A","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FPVNOD2AJTVXXQCJADWWHBORZJ","target":"record","payload":{"canonical_record":{"source":{"id":"1802.08089","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-22T15:06:51Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.ML"],"title_canon_sha256":"315779882f6816cebb967be56d625bd6d027e8bd41564a94f79bbad9962763e8","abstract_canon_sha256":"51d91227111aa8fcf89a763ee3975cbe0429a116824d34cd513dd9543ffe8750"},"schema_version":"1.0"},"canonical_sha256":"2bead70f404ceb7bc04900ed6385d1ca68d677223ab46f7797facfcd1c8d5fb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:00.207671Z","signature_b64":"HqZ2qvcl7+/2MA9MlygUCQSywi8/Iijnc0uZ800oXX8pPcOD0FrwCO4elFjTd4xP13jbgX9jRYC/QCGHc0pUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bead70f404ceb7bc04900ed6385d1ca68d677223ab46f7797facfcd1c8d5fb8","last_reissued_at":"2026-05-18T00:14:00.207066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:00.207066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.08089","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oD0YoYYtUJE0mxrS3q6K4SGrffRAHGv+AaesQguxXBKDbSvHNbr2WLA+eH3h+ubvait4265OkjlYRTsz8NWbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:00:52.026620Z"},"content_sha256":"92ebaac41af89983d99bdd1f969dcba10ba99abe13ec85672a47d86d9a310eb8","schema_version":"1.0","event_id":"sha256:92ebaac41af89983d99bdd1f969dcba10ba99abe13ec85672a47d86d9a310eb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FPVNOD2AJTVXXQCJADWWHBORZJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.ML"],"primary_cat":"math.OC","authors_text":"Andre Wibisono","submitted_at":"2018-02-22T15:06:51Z","abstract_excerpt":"We study sampling as optimization in the space of measures. We focus on gradient flow-based optimization with the Langevin dynamics as a case study. We investigate the source of the bias of the unadjusted Langevin algorithm (ULA) in discrete time, and consider how to remove or reduce the bias. We point out the difficulty is that the heat flow is exactly solvable, but neither its forward nor backward method is implementable in general, except for Gaussian data. We propose the symmetrized Langevin algorithm (SLA), which should have a smaller bias than ULA, at the price of implementing a proximal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08089","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bf2myQ7ECLlQbMDEi5zuP5U0HUYpyrqI7iVfcuQ90USQMcbD3atXC2tVN6yWozWFz7GwvgJj3Gw2Cn8T1sguBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:00:52.027329Z"},"content_sha256":"e75d2ae3151938e1a0bae223ca516be83e1774c16572629c29c89138ef0e6c56","schema_version":"1.0","event_id":"sha256:e75d2ae3151938e1a0bae223ca516be83e1774c16572629c29c89138ef0e6c56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPVNOD2AJTVXXQCJADWWHBORZJ/bundle.json","state_url":"https://pith.science/pith/FPVNOD2AJTVXXQCJADWWHBORZJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPVNOD2AJTVXXQCJADWWHBORZJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T19:00:52Z","links":{"resolver":"https://pith.science/pith/FPVNOD2AJTVXXQCJADWWHBORZJ","bundle":"https://pith.science/pith/FPVNOD2AJTVXXQCJADWWHBORZJ/bundle.json","state":"https://pith.science/pith/FPVNOD2AJTVXXQCJADWWHBORZJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPVNOD2AJTVXXQCJADWWHBORZJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FPVNOD2AJTVXXQCJADWWHBORZJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"51d91227111aa8fcf89a763ee3975cbe0429a116824d34cd513dd9543ffe8750","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-22T15:06:51Z","title_canon_sha256":"315779882f6816cebb967be56d625bd6d027e8bd41564a94f79bbad9962763e8"},"schema_version":"1.0","source":{"id":"1802.08089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.08089","created_at":"2026-05-18T00:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"1802.08089v2","created_at":"2026-05-18T00:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08089","created_at":"2026-05-18T00:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"FPVNOD2AJTVX","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FPVNOD2AJTVXXQCJ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FPVNOD2A","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:e75d2ae3151938e1a0bae223ca516be83e1774c16572629c29c89138ef0e6c56","target":"graph","created_at":"2026-05-18T00:14:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We study sampling as optimization in the space of measures. We focus on gradient flow-based optimization with the Langevin dynamics as a case study. We investigate the source of the bias of the unadjusted Langevin algorithm (ULA) in discrete time, and consider how to remove or reduce the bias. We point out the difficulty is that the heat flow is exactly solvable, but neither its forward nor backward method is implementable in general, except for Gaussian data. We propose the symmetrized Langevin algorithm (SLA), which should have a smaller bias than ULA, at the price of implementing a proximal","authors_text":"Andre Wibisono","cross_cats":["cs.IT","cs.LG","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-22T15:06:51Z","title":"Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08089","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:92ebaac41af89983d99bdd1f969dcba10ba99abe13ec85672a47d86d9a310eb8","target":"record","created_at":"2026-05-18T00:14:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"51d91227111aa8fcf89a763ee3975cbe0429a116824d34cd513dd9543ffe8750","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-22T15:06:51Z","title_canon_sha256":"315779882f6816cebb967be56d625bd6d027e8bd41564a94f79bbad9962763e8"},"schema_version":"1.0","source":{"id":"1802.08089","kind":"arxiv","version":2}},"canonical_sha256":"2bead70f404ceb7bc04900ed6385d1ca68d677223ab46f7797facfcd1c8d5fb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bead70f404ceb7bc04900ed6385d1ca68d677223ab46f7797facfcd1c8d5fb8","first_computed_at":"2026-05-18T00:14:00.207066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:00.207066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HqZ2qvcl7+/2MA9MlygUCQSywi8/Iijnc0uZ800oXX8pPcOD0FrwCO4elFjTd4xP13jbgX9jRYC/QCGHc0pUAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:00.207671Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.08089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92ebaac41af89983d99bdd1f969dcba10ba99abe13ec85672a47d86d9a310eb8","sha256:e75d2ae3151938e1a0bae223ca516be83e1774c16572629c29c89138ef0e6c56"],"state_sha256":"ec9c9d4ff1d6561376ad52f4b9448dfc7927a3a3c1d79d1aa90ec5ad29f75da4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Csb8gpHIdYvVk4MFmRMtnkXC1HdXyw3100jtfnpzMoZDI424TLI2MJw+32QAorHk6GENkUfN1bF40oiX7JioCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:00:52.030946Z","bundle_sha256":"b1525b3bf1bd33e747d0aee485913f0d5f762a24ff6fe477ff3afc5eb7cba4df"}}