{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:X62TVW7CTJZ5MK4G5UM2M4G3WR","short_pith_number":"pith:X62TVW7C","schema_version":"1.0","canonical_sha256":"bfb53adbe29a73d62b86ed19a670dbb4678e108ac59defa6665d640fd1f0edd3","source":{"kind":"arxiv","id":"1512.07962","version":3},"attestation_state":"computed","paper":{"title":"Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Chunyuan Li, David Carlson, Lawrence Carin, Zhe Gan","submitted_at":"2015-12-25T06:01:44Z","abstract_excerpt":"Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian analogs to popular stochastic optimization methods; however, this connection is not well studied. We explore this relationship by applying simulated annealing to an SGMCMC algorithm. Furthermore, we extend recent SG-MCMC methods with two key components: i) adaptive preconditioners (as in ADAgrad or RMSprop), and ii) adaptive element-wise momentum weights. The zero-temperature limit gives a novel stochastic optimization method with adaptive element-wise momentum weights, while conventional optimization methods only have"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1512.07962","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-12-25T06:01:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c713385f53fd3198a02835ad1b15208514187875cecaf34b6d47fec30bd9b37e","abstract_canon_sha256":"2197f7764c25ce252f9992ec5943ebc5779d5170a7b3cc1374487959e82061c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:45.644748Z","signature_b64":"gvmc5ZksaKpSxrZWFlM2hgv/R//Ca3IDRu4sxIp5EahijnKcmRmOjlbBo585SZwqcW4dIBsFAqQO3RXOI1GHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb53adbe29a73d62b86ed19a670dbb4678e108ac59defa6665d640fd1f0edd3","last_reissued_at":"2026-05-18T01:09:45.644039Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:45.644039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Chunyuan Li, David Carlson, Lawrence Carin, Zhe Gan","submitted_at":"2015-12-25T06:01:44Z","abstract_excerpt":"Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian analogs to popular stochastic optimization methods; however, this connection is not well studied. We explore this relationship by applying simulated annealing to an SGMCMC algorithm. Furthermore, we extend recent SG-MCMC methods with two key components: i) adaptive preconditioners (as in ADAgrad or RMSprop), and ii) adaptive element-wise momentum weights. The zero-temperature limit gives a novel stochastic optimization method with adaptive element-wise momentum weights, while conventional optimization methods only have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.07962","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1512.07962","created_at":"2026-05-18T01:09:45.644147+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.07962v3","created_at":"2026-05-18T01:09:45.644147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.07962","created_at":"2026-05-18T01:09:45.644147+00:00"},{"alias_kind":"pith_short_12","alias_value":"X62TVW7CTJZ5","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"X62TVW7CTJZ5MK4G","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"X62TVW7C","created_at":"2026-05-18T12:29:47.479230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR","json":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR.json","graph_json":"https://pith.science/api/pith-number/X62TVW7CTJZ5MK4G5UM2M4G3WR/graph.json","events_json":"https://pith.science/api/pith-number/X62TVW7CTJZ5MK4G5UM2M4G3WR/events.json","paper":"https://pith.science/paper/X62TVW7C"},"agent_actions":{"view_html":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR","download_json":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR.json","view_paper":"https://pith.science/paper/X62TVW7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.07962&json=true","fetch_graph":"https://pith.science/api/pith-number/X62TVW7CTJZ5MK4G5UM2M4G3WR/graph.json","fetch_events":"https://pith.science/api/pith-number/X62TVW7CTJZ5MK4G5UM2M4G3WR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR/action/storage_attestation","attest_author":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR/action/author_attestation","sign_citation":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR/action/citation_signature","submit_replication":"https://pith.science/pith/X62TVW7CTJZ5MK4G5UM2M4G3WR/action/replication_record"}},"created_at":"2026-05-18T01:09:45.644147+00:00","updated_at":"2026-05-18T01:09:45.644147+00:00"}