{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PEP65JEECYNK2XN3MKNSXPGGBY","short_pith_number":"pith:PEP65JEE","canonical_record":{"source":{"id":"2303.01370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-03-01T07:36:03Z","cross_cats_sorted":["math.PR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"be44214ab8ef76d793a9a4b3e8250fc3096fa10b66d29ceea32899fe6aab3dee","abstract_canon_sha256":"7c55416ac7f0a95925145c9659ae7978555248154105e8ddb181ad9d7e60fa21"},"schema_version":"1.0"},"canonical_sha256":"791feea484161aad5dbb629b2bbcc60e398c8d593f4a4d19a4f1dd90b22207be","source":{"kind":"arxiv","id":"2303.01370","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01370","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01370v1","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01370","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"PEP65JEECYNK","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"pith_short_16","alias_value":"PEP65JEECYNK2XN3","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"pith_short_8","alias_value":"PEP65JEE","created_at":"2026-07-05T05:47:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PEP65JEECYNK2XN3MKNSXPGGBY","target":"record","payload":{"canonical_record":{"source":{"id":"2303.01370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-03-01T07:36:03Z","cross_cats_sorted":["math.PR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"be44214ab8ef76d793a9a4b3e8250fc3096fa10b66d29ceea32899fe6aab3dee","abstract_canon_sha256":"7c55416ac7f0a95925145c9659ae7978555248154105e8ddb181ad9d7e60fa21"},"schema_version":"1.0"},"canonical_sha256":"791feea484161aad5dbb629b2bbcc60e398c8d593f4a4d19a4f1dd90b22207be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:30.094379Z","signature_b64":"SGi71MSpPhvgoXG3DTHPbEd42bJpf/Bm4GHOKdmA3ftOstLxVZDIpTOTxB5s41DG+Y7V1Z7GQX+LzEnjri9vAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"791feea484161aad5dbb629b2bbcc60e398c8d593f4a4d19a4f1dd90b22207be","last_reissued_at":"2026-07-05T05:47:30.093909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:30.093909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.01370","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDS7A/Y9x71XfIguH9/+dI6B4VH5ue0z/FbR+zV16JWxtvMFrbMIzlahsQUiEREtagAkx6oWmMFGC9gULGpjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:02:11.397687Z"},"content_sha256":"b1bc54c1b04835aa4741b74a8ed71e0bc69c80a9addc77572ede67bff9a1b2d4","schema_version":"1.0","event_id":"sha256:b1bc54c1b04835aa4741b74a8ed71e0bc69c80a9addc77572ede67bff9a1b2d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PEP65JEECYNK2XN3MKNSXPGGBY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non asymptotic analysis of Adaptive stochastic gradient algorithms and applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"math.OC","authors_text":"Antoine Godichon-Baggioni (LPSM (UMR\\_8001)), Pierre Tarrago (LPSM (UMR\\_8001))","submitted_at":"2023-03-01T07:36:03Z","abstract_excerpt":"In stochastic optimization, a common tool to deal sequentially with large sample is to consider the well-known stochastic gradient algorithm. Nevertheless, since the stepsequence is the same for each direction, this can lead to bad results in practice in case of ill-conditionned problem. To overcome this, adaptive gradient algorithms such that Adagrad or Stochastic Newton algorithms should be prefered. This paper is devoted to the non asymptotic analyis of these adaptive gradient algorithms for strongly convex objective. All the theoretical results will be adapted to linear regression and regu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01370","kind":"arxiv","version":1},"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/2303.01370/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":"2026-07-05T05:47:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wa7oRmXHoXSGSQkgblT7jj7y/2yyZT3358478Tb+v6JuSteMKYbUBzPQyQIQJeMG0HxsWLgH/sH41+X9Lh+OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:02:11.398377Z"},"content_sha256":"1f553fc030de99cefe1696dea3ed83b06fa19be38ebb4d94ee35f9c55c6e9a3a","schema_version":"1.0","event_id":"sha256:1f553fc030de99cefe1696dea3ed83b06fa19be38ebb4d94ee35f9c55c6e9a3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEP65JEECYNK2XN3MKNSXPGGBY/bundle.json","state_url":"https://pith.science/pith/PEP65JEECYNK2XN3MKNSXPGGBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEP65JEECYNK2XN3MKNSXPGGBY/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":"2026-08-18T12:02:11Z","links":{"resolver":"https://pith.science/pith/PEP65JEECYNK2XN3MKNSXPGGBY","bundle":"https://pith.science/pith/PEP65JEECYNK2XN3MKNSXPGGBY/bundle.json","state":"https://pith.science/pith/PEP65JEECYNK2XN3MKNSXPGGBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEP65JEECYNK2XN3MKNSXPGGBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PEP65JEECYNK2XN3MKNSXPGGBY","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":"7c55416ac7f0a95925145c9659ae7978555248154105e8ddb181ad9d7e60fa21","cross_cats_sorted":["math.PR","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-03-01T07:36:03Z","title_canon_sha256":"be44214ab8ef76d793a9a4b3e8250fc3096fa10b66d29ceea32899fe6aab3dee"},"schema_version":"1.0","source":{"id":"2303.01370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01370","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01370v1","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01370","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"PEP65JEECYNK","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"pith_short_16","alias_value":"PEP65JEECYNK2XN3","created_at":"2026-07-05T05:47:30Z"},{"alias_kind":"pith_short_8","alias_value":"PEP65JEE","created_at":"2026-07-05T05:47:30Z"}],"graph_snapshots":[{"event_id":"sha256:1f553fc030de99cefe1696dea3ed83b06fa19be38ebb4d94ee35f9c55c6e9a3a","target":"graph","created_at":"2026-07-05T05:47:30Z","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/2303.01370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In stochastic optimization, a common tool to deal sequentially with large sample is to consider the well-known stochastic gradient algorithm. Nevertheless, since the stepsequence is the same for each direction, this can lead to bad results in practice in case of ill-conditionned problem. To overcome this, adaptive gradient algorithms such that Adagrad or Stochastic Newton algorithms should be prefered. This paper is devoted to the non asymptotic analyis of these adaptive gradient algorithms for strongly convex objective. All the theoretical results will be adapted to linear regression and regu","authors_text":"Antoine Godichon-Baggioni (LPSM (UMR\\_8001)), Pierre Tarrago (LPSM (UMR\\_8001))","cross_cats":["math.PR","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-03-01T07:36:03Z","title":"Non asymptotic analysis of Adaptive stochastic gradient algorithms and applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01370","kind":"arxiv","version":1},"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:b1bc54c1b04835aa4741b74a8ed71e0bc69c80a9addc77572ede67bff9a1b2d4","target":"record","created_at":"2026-07-05T05:47:30Z","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":"7c55416ac7f0a95925145c9659ae7978555248154105e8ddb181ad9d7e60fa21","cross_cats_sorted":["math.PR","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-03-01T07:36:03Z","title_canon_sha256":"be44214ab8ef76d793a9a4b3e8250fc3096fa10b66d29ceea32899fe6aab3dee"},"schema_version":"1.0","source":{"id":"2303.01370","kind":"arxiv","version":1}},"canonical_sha256":"791feea484161aad5dbb629b2bbcc60e398c8d593f4a4d19a4f1dd90b22207be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"791feea484161aad5dbb629b2bbcc60e398c8d593f4a4d19a4f1dd90b22207be","first_computed_at":"2026-07-05T05:47:30.093909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:30.093909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SGi71MSpPhvgoXG3DTHPbEd42bJpf/Bm4GHOKdmA3ftOstLxVZDIpTOTxB5s41DG+Y7V1Z7GQX+LzEnjri9vAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:30.094379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.01370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1bc54c1b04835aa4741b74a8ed71e0bc69c80a9addc77572ede67bff9a1b2d4","sha256:1f553fc030de99cefe1696dea3ed83b06fa19be38ebb4d94ee35f9c55c6e9a3a"],"state_sha256":"3fefa60f465d7c81126a8e4cc47e583fa46b182102dfec57e4376b3c44f65b1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8hbz64eknJFBm4Jo1eXa83fW3B2Jvc1K4YqoISB8XxzQPKbbY55oND416yyCHy/+xr0z8ySHoe/Rg40HBmiwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:02:11.405174Z","bundle_sha256":"5090a69d9cb6234ffcfee322f19f72039ddbc764be0527a5f1991b7387e856ff"}}