{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5UILCLCCHPDKL4XLLUBOKZ5EKQ","short_pith_number":"pith:5UILCLCC","schema_version":"1.0","canonical_sha256":"ed10b12c423bc6a5f2eb5d02e567a4542cc71735bb5fd43f57f5e2d7cd08888f","source":{"kind":"arxiv","id":"2006.11653","version":2},"attestation_state":"computed","paper":{"title":"Towards Understanding Label Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Li, Qi Qian, Rong Jin, Yi Xu, Yuanhong Xu","submitted_at":"2020-06-20T20:36:17Z","abstract_excerpt":"Label smoothing regularization (LSR) has a great success in training deep neural networks by stochastic algorithms such as stochastic gradient descent and its variants. However, the theoretical understanding of its power from the view of optimization is still rare. This study opens the door to a deep understanding of LSR by initiating the analysis. In this paper, we analyze the convergence behaviors of stochastic gradient descent with label smoothing regularization for solving non-convex problems and show that an appropriate LSR can help to speed up the convergence by reducing the variance. Mo"},"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":"2006.11653","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T20:36:17Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"dd0d79b9fb0283b9d02c0e55c4968f0f1c7799377c1920806de8360065598bd7","abstract_canon_sha256":"83537ff5da456a9efe7b79884575681397f52345d003f4ea5e1f13389e6e8f6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:59.312714Z","signature_b64":"rh6+rA+Q5G/Ut0UNZm3pPKHjdEVWgf/SL5qY1kd9+XPsT6+HBOpgXKAA2E7F/+B4UbmHO/i2t+8KOgSuVc+0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed10b12c423bc6a5f2eb5d02e567a4542cc71735bb5fd43f57f5e2d7cd08888f","last_reissued_at":"2026-07-05T01:39:59.312225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:59.312225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding Label Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Li, Qi Qian, Rong Jin, Yi Xu, Yuanhong Xu","submitted_at":"2020-06-20T20:36:17Z","abstract_excerpt":"Label smoothing regularization (LSR) has a great success in training deep neural networks by stochastic algorithms such as stochastic gradient descent and its variants. However, the theoretical understanding of its power from the view of optimization is still rare. This study opens the door to a deep understanding of LSR by initiating the analysis. In this paper, we analyze the convergence behaviors of stochastic gradient descent with label smoothing regularization for solving non-convex problems and show that an appropriate LSR can help to speed up the convergence by reducing the variance. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11653","kind":"arxiv","version":2},"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/2006.11653/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":"2006.11653","created_at":"2026-07-05T01:39:59.312282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11653v2","created_at":"2026-07-05T01:39:59.312282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11653","created_at":"2026-07-05T01:39:59.312282+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UILCLCCHPDK","created_at":"2026-07-05T01:39:59.312282+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UILCLCCHPDKL4XL","created_at":"2026-07-05T01:39:59.312282+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UILCLCC","created_at":"2026-07-05T01:39:59.312282+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/5UILCLCCHPDKL4XLLUBOKZ5EKQ","json":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ.json","graph_json":"https://pith.science/api/pith-number/5UILCLCCHPDKL4XLLUBOKZ5EKQ/graph.json","events_json":"https://pith.science/api/pith-number/5UILCLCCHPDKL4XLLUBOKZ5EKQ/events.json","paper":"https://pith.science/paper/5UILCLCC"},"agent_actions":{"view_html":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ","download_json":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ.json","view_paper":"https://pith.science/paper/5UILCLCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11653&json=true","fetch_graph":"https://pith.science/api/pith-number/5UILCLCCHPDKL4XLLUBOKZ5EKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5UILCLCCHPDKL4XLLUBOKZ5EKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ/action/storage_attestation","attest_author":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ/action/author_attestation","sign_citation":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ/action/citation_signature","submit_replication":"https://pith.science/pith/5UILCLCCHPDKL4XLLUBOKZ5EKQ/action/replication_record"}},"created_at":"2026-07-05T01:39:59.312282+00:00","updated_at":"2026-07-05T01:39:59.312282+00:00"}