{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:X4SJ44TPMPPRVGU7H4DADKTG6I","short_pith_number":"pith:X4SJ44TP","canonical_record":{"source":{"id":"2007.14294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-28T15:06:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"542bc5700b4a48920fac21f362de067b304e2cadea39396d6fafe4e9aa51860d","abstract_canon_sha256":"99fb11557b5e62b423496f00450ebcb022315ddcf3ae6201c5d04a28b80a66ce"},"schema_version":"1.0"},"canonical_sha256":"bf249e726f63df1a9a9f3f0601aa66f21e9b0b0fe96fc7ff838e4d23af5bb64f","source":{"kind":"arxiv","id":"2007.14294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14294","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14294v1","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14294","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"X4SJ44TPMPPR","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"X4SJ44TPMPPRVGU7","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"X4SJ44TP","created_at":"2026-07-05T01:22:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:X4SJ44TPMPPRVGU7H4DADKTG6I","target":"record","payload":{"canonical_record":{"source":{"id":"2007.14294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-28T15:06:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"542bc5700b4a48920fac21f362de067b304e2cadea39396d6fafe4e9aa51860d","abstract_canon_sha256":"99fb11557b5e62b423496f00450ebcb022315ddcf3ae6201c5d04a28b80a66ce"},"schema_version":"1.0"},"canonical_sha256":"bf249e726f63df1a9a9f3f0601aa66f21e9b0b0fe96fc7ff838e4d23af5bb64f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:57.407058Z","signature_b64":"PTOWnrxuUXIuIxonO/DIa+BDhCDwhbTX05PJTmh8kPbKiXKQUfBnv23CZeNOVWvZbC8c1tV6yLUoSDm7EYfgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf249e726f63df1a9a9f3f0601aa66f21e9b0b0fe96fc7ff838e4d23af5bb64f","last_reissued_at":"2026-07-05T01:22:57.406607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:57.406607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.14294","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":"2026-07-05T01:22:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JjxXxInI4Fu6NtbnGPJ3qlbiG7GumLOKr4ZD8KHH0mkzrMlNvQAO7Qe26t3dYxR1l3o6+iRjdCVke/JsTO5oDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:52:57.600262Z"},"content_sha256":"aa2cac36c2072a26c633165ecc5473e793e19a62fb5374c6c32e3c8401b64834","schema_version":"1.0","event_id":"sha256:aa2cac36c2072a26c633165ecc5473e793e19a62fb5374c6c32e3c8401b64834"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:X4SJ44TPMPPRVGU7H4DADKTG6I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A High Probability Analysis of Adaptive SGD with Momentum","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Francesco Orabona, Xiaoyu Li","submitted_at":"2020-07-28T15:06:22Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the enormous success of these methods, our theoretical understanding of these variants in the nonconvex setting is not complete, with most of the results only proving convergence in expectation and with strong assumptions on the stochastic gradients. In this paper, we present a high probability analysis for adaptive and momentum algorithms, under weak assumptions on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14294","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/2007.14294/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":"2026-07-05T01:22:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JD2pHzEJaLRCuaxNYQ1u1F7Pa16idLaG1w9WDtxpC7m76gymQ6XcMgu1UUQZT4PEj8HhifwZYPdrqchtOH/SAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:52:57.600847Z"},"content_sha256":"5b3e509711ebea6a3b6221bc523482cd94fc6584e40dc834a2487a83d7c365d6","schema_version":"1.0","event_id":"sha256:5b3e509711ebea6a3b6221bc523482cd94fc6584e40dc834a2487a83d7c365d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4SJ44TPMPPRVGU7H4DADKTG6I/bundle.json","state_url":"https://pith.science/pith/X4SJ44TPMPPRVGU7H4DADKTG6I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4SJ44TPMPPRVGU7H4DADKTG6I/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":"2026-08-09T17:52:57Z","links":{"resolver":"https://pith.science/pith/X4SJ44TPMPPRVGU7H4DADKTG6I","bundle":"https://pith.science/pith/X4SJ44TPMPPRVGU7H4DADKTG6I/bundle.json","state":"https://pith.science/pith/X4SJ44TPMPPRVGU7H4DADKTG6I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4SJ44TPMPPRVGU7H4DADKTG6I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:X4SJ44TPMPPRVGU7H4DADKTG6I","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":"99fb11557b5e62b423496f00450ebcb022315ddcf3ae6201c5d04a28b80a66ce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-28T15:06:22Z","title_canon_sha256":"542bc5700b4a48920fac21f362de067b304e2cadea39396d6fafe4e9aa51860d"},"schema_version":"1.0","source":{"id":"2007.14294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14294","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14294v1","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14294","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"X4SJ44TPMPPR","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"X4SJ44TPMPPRVGU7","created_at":"2026-07-05T01:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"X4SJ44TP","created_at":"2026-07-05T01:22:57Z"}],"graph_snapshots":[{"event_id":"sha256:5b3e509711ebea6a3b6221bc523482cd94fc6584e40dc834a2487a83d7c365d6","target":"graph","created_at":"2026-07-05T01:22:57Z","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/2007.14294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic Gradient Descent (SGD) and its variants are the most used algorithms in machine learning applications. In particular, SGD with adaptive learning rates and momentum is the industry standard to train deep networks. Despite the enormous success of these methods, our theoretical understanding of these variants in the nonconvex setting is not complete, with most of the results only proving convergence in expectation and with strong assumptions on the stochastic gradients. In this paper, we present a high probability analysis for adaptive and momentum algorithms, under weak assumptions on","authors_text":"Francesco Orabona, Xiaoyu Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-28T15:06:22Z","title":"A High Probability Analysis of Adaptive SGD with Momentum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14294","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:aa2cac36c2072a26c633165ecc5473e793e19a62fb5374c6c32e3c8401b64834","target":"record","created_at":"2026-07-05T01:22:57Z","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":"99fb11557b5e62b423496f00450ebcb022315ddcf3ae6201c5d04a28b80a66ce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-28T15:06:22Z","title_canon_sha256":"542bc5700b4a48920fac21f362de067b304e2cadea39396d6fafe4e9aa51860d"},"schema_version":"1.0","source":{"id":"2007.14294","kind":"arxiv","version":1}},"canonical_sha256":"bf249e726f63df1a9a9f3f0601aa66f21e9b0b0fe96fc7ff838e4d23af5bb64f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf249e726f63df1a9a9f3f0601aa66f21e9b0b0fe96fc7ff838e4d23af5bb64f","first_computed_at":"2026-07-05T01:22:57.406607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:22:57.406607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PTOWnrxuUXIuIxonO/DIa+BDhCDwhbTX05PJTmh8kPbKiXKQUfBnv23CZeNOVWvZbC8c1tV6yLUoSDm7EYfgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:22:57.407058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.14294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa2cac36c2072a26c633165ecc5473e793e19a62fb5374c6c32e3c8401b64834","sha256:5b3e509711ebea6a3b6221bc523482cd94fc6584e40dc834a2487a83d7c365d6"],"state_sha256":"94c38415ed8ce3c28710eac3e7d690be322bb314b552b5aa326c70f3b70cb484"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+6xbyjnVpx88e0frn177AgEtldzqnQPuXnNnlZMwZf078iQ8Fi5LaWjCqzVm1owxGwqOf41iLAkXvFfBs36Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:52:57.605940Z","bundle_sha256":"4313dd8ebd8e8da35a0863cff0b7e3a4ba904fc4aa2c8502c75354d224bfb4cb"}}