{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:432K24ZJYQLBKK44HHAY5ZFACJ","short_pith_number":"pith:432K24ZJ","schema_version":"1.0","canonical_sha256":"e6f4ad7329c416152b9c39c18ee4a0126eeb07c1fa8f9758b2be4ed9dcec715a","source":{"kind":"arxiv","id":"2307.13680","version":1},"attestation_state":"computed","paper":{"title":"High Probability Analysis for Non-Convex Stochastic Optimization with Clipping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shaojie Li, Yong Liu","submitted_at":"2023-07-25T17:36:56Z","abstract_excerpt":"Gradient clipping is a commonly used technique to stabilize the training process of neural networks. A growing body of studies has shown that gradient clipping is a promising technique for dealing with the heavy-tailed behavior that emerged in stochastic optimization as well. While gradient clipping is significant, its theoretical guarantees are scarce. Most theoretical guarantees only provide an in-expectation analysis and only focus on optimization performance. In this paper, we provide high probability analysis in the non-convex setting and derive the optimization bound and the generalizati"},"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":"2307.13680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-25T17:36:56Z","cross_cats_sorted":[],"title_canon_sha256":"5faae9342350e6beae4f64c89b2c745c263536b9c456cf0149ea644dc497f68b","abstract_canon_sha256":"ce638573082021e9d08e95b431295c2c856af9568552f78dfc0bdaf606105c10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:42.930658Z","signature_b64":"fduPfDuoUTLRr/63RoVLTX7XQeLS1tVM09dNU8SKfB0QBzdZ/wSpgY+A5yo69sevaZBy3+HqiunsutjGyyQmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6f4ad7329c416152b9c39c18ee4a0126eeb07c1fa8f9758b2be4ed9dcec715a","last_reissued_at":"2026-07-05T06:34:42.930228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:42.930228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High Probability Analysis for Non-Convex Stochastic Optimization with Clipping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shaojie Li, Yong Liu","submitted_at":"2023-07-25T17:36:56Z","abstract_excerpt":"Gradient clipping is a commonly used technique to stabilize the training process of neural networks. A growing body of studies has shown that gradient clipping is a promising technique for dealing with the heavy-tailed behavior that emerged in stochastic optimization as well. While gradient clipping is significant, its theoretical guarantees are scarce. Most theoretical guarantees only provide an in-expectation analysis and only focus on optimization performance. In this paper, we provide high probability analysis in the non-convex setting and derive the optimization bound and the generalizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13680","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/2307.13680/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.13680","created_at":"2026-07-05T06:34:42.930290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13680v1","created_at":"2026-07-05T06:34:42.930290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13680","created_at":"2026-07-05T06:34:42.930290+00:00"},{"alias_kind":"pith_short_12","alias_value":"432K24ZJYQLB","created_at":"2026-07-05T06:34:42.930290+00:00"},{"alias_kind":"pith_short_16","alias_value":"432K24ZJYQLBKK44","created_at":"2026-07-05T06:34:42.930290+00:00"},{"alias_kind":"pith_short_8","alias_value":"432K24ZJ","created_at":"2026-07-05T06:34:42.930290+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/432K24ZJYQLBKK44HHAY5ZFACJ","json":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ.json","graph_json":"https://pith.science/api/pith-number/432K24ZJYQLBKK44HHAY5ZFACJ/graph.json","events_json":"https://pith.science/api/pith-number/432K24ZJYQLBKK44HHAY5ZFACJ/events.json","paper":"https://pith.science/paper/432K24ZJ"},"agent_actions":{"view_html":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ","download_json":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ.json","view_paper":"https://pith.science/paper/432K24ZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13680&json=true","fetch_graph":"https://pith.science/api/pith-number/432K24ZJYQLBKK44HHAY5ZFACJ/graph.json","fetch_events":"https://pith.science/api/pith-number/432K24ZJYQLBKK44HHAY5ZFACJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ/action/storage_attestation","attest_author":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ/action/author_attestation","sign_citation":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ/action/citation_signature","submit_replication":"https://pith.science/pith/432K24ZJYQLBKK44HHAY5ZFACJ/action/replication_record"}},"created_at":"2026-07-05T06:34:42.930290+00:00","updated_at":"2026-07-05T06:34:42.930290+00:00"}