{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7N2ZNSA6RD7S2RI4A6ADI46LRY","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":"56464e4d824873756c212c142b505f29eb7505337a90aa93fe256c69e8b46e75","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-05-21T14:40:43Z","title_canon_sha256":"c501444c3b577368dac4ec89e71cd6c80f6cc5ed58eb80f78ca11fe598093ac6"},"schema_version":"1.0","source":{"id":"2305.12475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12475","created_at":"2026-07-05T06:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12475v1","created_at":"2026-07-05T06:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12475","created_at":"2026-07-05T06:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"7N2ZNSA6RD7S","created_at":"2026-07-05T06:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"7N2ZNSA6RD7S2RI4","created_at":"2026-07-05T06:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"7N2ZNSA6","created_at":"2026-07-05T06:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:c39cedf359d74db7eb4e18137cfa85f31a842052d07edb2b5e3d92e6d13aa4a9","target":"graph","created_at":"2026-07-05T06:12:11Z","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/2305.12475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The classical analysis of Stochastic Gradient Descent (SGD) with polynomially decaying stepsize $\\eta_t = \\eta/\\sqrt{t}$ relies on well-tuned $\\eta$ depending on problem parameters such as Lipschitz smoothness constant, which is often unknown in practice. In this work, we prove that SGD with arbitrary $\\eta > 0$, referred to as untuned SGD, still attains an order-optimal convergence rate $\\widetilde{O}(T^{-1/4})$ in terms of gradient norm for minimizing smooth objectives. Unfortunately, it comes at the expense of a catastrophic exponential dependence on the smoothness constant, which we show i","authors_text":"Ilyas Fatkhullin, Junchi Yang, Niao He, Xiang Li","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-05-21T14:40:43Z","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12475","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":"sha256:7efa764447e5f6bb4a36f5e6d0aff2aa7eff8e6e553c01f65926e3732065c6b4","target":"record","created_at":"2026-07-05T06:12:11Z","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":"56464e4d824873756c212c142b505f29eb7505337a90aa93fe256c69e8b46e75","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-05-21T14:40:43Z","title_canon_sha256":"c501444c3b577368dac4ec89e71cd6c80f6cc5ed58eb80f78ca11fe598093ac6"},"schema_version":"1.0","source":{"id":"2305.12475","kind":"arxiv","version":1}},"canonical_sha256":"fb7596c81e88ff2d451c07803473cb8e041dc5beb3cf0e072e05d5dbd637d497","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb7596c81e88ff2d451c07803473cb8e041dc5beb3cf0e072e05d5dbd637d497","first_computed_at":"2026-07-05T06:12:11.093542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:11.093542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+maQWdak9+NkiNeSu41UaQVTq7KgTgVEUR3vUnUOwsZThnZ/VlPcJAG1m56iWeV4X1BZeG8tHuyKCV1lUdguCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:11.093948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7efa764447e5f6bb4a36f5e6d0aff2aa7eff8e6e553c01f65926e3732065c6b4","sha256:c39cedf359d74db7eb4e18137cfa85f31a842052d07edb2b5e3d92e6d13aa4a9"],"state_sha256":"1212c314bdf16cd3f93bce17fbeddf104a7d695a3ce65484d48d815c56ad5974"}