{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RZENQXWJTSFISRFQTFCLV645XR","short_pith_number":"pith:RZENQXWJ","canonical_record":{"source":{"id":"2306.14522","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-26T08:54:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b39a81e63ae71f2b191ae6346a45a81c5c23fe7d9273c8945591ecf6deae506d","abstract_canon_sha256":"89a35ab2926921f58783500dcd47144735c9f048035756c99cbbb1c2b932f5cb"},"schema_version":"1.0"},"canonical_sha256":"8e48d85ec99c8a8944b09944bafb9dbc40f8ce77b628ebdfbc75636c6c01dad2","source":{"kind":"arxiv","id":"2306.14522","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14522","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14522v5","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14522","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"RZENQXWJTSFI","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"pith_short_16","alias_value":"RZENQXWJTSFISRFQ","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"pith_short_8","alias_value":"RZENQXWJ","created_at":"2026-07-05T10:02:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RZENQXWJTSFISRFQTFCLV645XR","target":"record","payload":{"canonical_record":{"source":{"id":"2306.14522","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-26T08:54:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b39a81e63ae71f2b191ae6346a45a81c5c23fe7d9273c8945591ecf6deae506d","abstract_canon_sha256":"89a35ab2926921f58783500dcd47144735c9f048035756c99cbbb1c2b932f5cb"},"schema_version":"1.0"},"canonical_sha256":"8e48d85ec99c8a8944b09944bafb9dbc40f8ce77b628ebdfbc75636c6c01dad2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:40.545457Z","signature_b64":"mUHtau0H/p+Kf4YC9hK3/WQgHUpaIU2eCgF3dbh/1JWG8PDWoXXtorIgR2fCpUY6uOtXfK/yBvZp69h9tC8PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e48d85ec99c8a8944b09944bafb9dbc40f8ce77b628ebdfbc75636c6c01dad2","last_reissued_at":"2026-07-05T10:02:40.545021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:40.545021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.14522","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9vwHH2WHz88p1h+gJVmlXn+3S1OdB8scly2jrYtR3YpQl0lTeLbBEJWu9LdOiIOQIAsuAzV1O/fm9iGZOBoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:07:04.765406Z"},"content_sha256":"ba1e9d138a4c0a897928e1c55ef21f8717bfbf008407c507ad280f9d5b211e47","schema_version":"1.0","event_id":"sha256:ba1e9d138a4c0a897928e1c55ef21f8717bfbf008407c507ad280f9d5b211e47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RZENQXWJTSFISRFQTFCLV645XR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Jingyang Li, Kim-Chuan Toh, Kuangyu Ding","submitted_at":"2023-06-26T08:54:46Z","abstract_excerpt":"Stochastic gradient methods for minimizing nonconvex composite objective functions typically rely on the Lipschitz smoothness of the differentiable part, but this assumption fails in many important problem classes like quadratic inverse problems and neural network training, leading to instability of the algorithms in both theory and practice. To address this, we propose a family of stochastic Bregman proximal gradient (SBPG) methods that only require smooth adaptivity. SBPG replaces the quadratic approximation in SGD with a Bregman proximity measure, offering a better approximation model that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14522","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.14522/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T10:02:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jb6d86/U/DXW68DnGHvlJ/LyV9ZiV7EQaiSVrRU02A/BA6o3rWQpIia7thLO3b/BXmJgNtBMHWSveelAhoJmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:07:04.766207Z"},"content_sha256":"f4dc05257fb095461e01c5d7e12a27fdf4c12addbe0f374e2221a3a9cbec638b","schema_version":"1.0","event_id":"sha256:f4dc05257fb095461e01c5d7e12a27fdf4c12addbe0f374e2221a3a9cbec638b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZENQXWJTSFISRFQTFCLV645XR/bundle.json","state_url":"https://pith.science/pith/RZENQXWJTSFISRFQTFCLV645XR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZENQXWJTSFISRFQTFCLV645XR/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":"2026-08-11T00:07:04Z","links":{"resolver":"https://pith.science/pith/RZENQXWJTSFISRFQTFCLV645XR","bundle":"https://pith.science/pith/RZENQXWJTSFISRFQTFCLV645XR/bundle.json","state":"https://pith.science/pith/RZENQXWJTSFISRFQTFCLV645XR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZENQXWJTSFISRFQTFCLV645XR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RZENQXWJTSFISRFQTFCLV645XR","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":"89a35ab2926921f58783500dcd47144735c9f048035756c99cbbb1c2b932f5cb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-26T08:54:46Z","title_canon_sha256":"b39a81e63ae71f2b191ae6346a45a81c5c23fe7d9273c8945591ecf6deae506d"},"schema_version":"1.0","source":{"id":"2306.14522","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14522","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14522v5","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14522","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"pith_short_12","alias_value":"RZENQXWJTSFI","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"pith_short_16","alias_value":"RZENQXWJTSFISRFQ","created_at":"2026-07-05T10:02:40Z"},{"alias_kind":"pith_short_8","alias_value":"RZENQXWJ","created_at":"2026-07-05T10:02:40Z"}],"graph_snapshots":[{"event_id":"sha256:f4dc05257fb095461e01c5d7e12a27fdf4c12addbe0f374e2221a3a9cbec638b","target":"graph","created_at":"2026-07-05T10:02:40Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.14522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient methods for minimizing nonconvex composite objective functions typically rely on the Lipschitz smoothness of the differentiable part, but this assumption fails in many important problem classes like quadratic inverse problems and neural network training, leading to instability of the algorithms in both theory and practice. To address this, we propose a family of stochastic Bregman proximal gradient (SBPG) methods that only require smooth adaptivity. SBPG replaces the quadratic approximation in SGD with a Bregman proximity measure, offering a better approximation model that ","authors_text":"Jingyang Li, Kim-Chuan Toh, Kuangyu Ding","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-26T08:54:46Z","title":"Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14522","kind":"arxiv","version":5},"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:ba1e9d138a4c0a897928e1c55ef21f8717bfbf008407c507ad280f9d5b211e47","target":"record","created_at":"2026-07-05T10:02:40Z","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":"89a35ab2926921f58783500dcd47144735c9f048035756c99cbbb1c2b932f5cb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2023-06-26T08:54:46Z","title_canon_sha256":"b39a81e63ae71f2b191ae6346a45a81c5c23fe7d9273c8945591ecf6deae506d"},"schema_version":"1.0","source":{"id":"2306.14522","kind":"arxiv","version":5}},"canonical_sha256":"8e48d85ec99c8a8944b09944bafb9dbc40f8ce77b628ebdfbc75636c6c01dad2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e48d85ec99c8a8944b09944bafb9dbc40f8ce77b628ebdfbc75636c6c01dad2","first_computed_at":"2026-07-05T10:02:40.545021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:40.545021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mUHtau0H/p+Kf4YC9hK3/WQgHUpaIU2eCgF3dbh/1JWG8PDWoXXtorIgR2fCpUY6uOtXfK/yBvZp69h9tC8PDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:40.545457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14522","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba1e9d138a4c0a897928e1c55ef21f8717bfbf008407c507ad280f9d5b211e47","sha256:f4dc05257fb095461e01c5d7e12a27fdf4c12addbe0f374e2221a3a9cbec638b"],"state_sha256":"2462e7a51a2b24a57f1f63ccb169af418092a76da394c772699dabeb5d106244"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dquLbYDcf7Fgh3uzCh6rHb/RhSUxAXfQ2M099UM+5heb5yBdjlivYNPqICKnpghlZtqRqwyGrqdOWSWvbcioBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:07:04.774013Z","bundle_sha256":"fbf3dabf6fe5cfb710c098b59bf64b30ae54fd60849b03d5a84ddee96910bba6"}}