{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DK7DHN7JU4QRHVB4VXTUB56MFW","short_pith_number":"pith:DK7DHN7J","schema_version":"1.0","canonical_sha256":"1abe33b7e9a72113d43cade740f7cc2d8ce0f62355bc97cec7b1f15af0debcca","source":{"kind":"arxiv","id":"2102.00236","version":1},"attestation_state":"computed","paper":{"title":"Parameter-free Stochastic Optimization of Variationally Coherent Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"D\\'avid P\\'al, Francesco Orabona","submitted_at":"2021-01-30T15:05:34Z","abstract_excerpt":"We design and analyze an algorithm for first-order stochastic optimization of a large class of functions on $\\mathbb{R}^d$. In particular, we consider the \\emph{variationally coherent} functions which can be convex or non-convex. The iterates of our algorithm on variationally coherent functions converge almost surely to the global minimizer $\\boldsymbol{x}^*$. Additionally, the very same algorithm with the same hyperparameters, after $T$ iterations guarantees on convex functions that the expected suboptimality gap is bounded by $\\widetilde{O}(\\|\\boldsymbol{x}^* - \\boldsymbol{x}_0\\| T^{-1/2+\\ep"},"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":"2102.00236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-01-30T15:05:34Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"9739501ac71e15450f885a1ce68e8bbecd69824a91343fea9f1feb921ac7972f","abstract_canon_sha256":"23e633be95b2ffa5ca23ff4aca9a902c2d190368c4ec4d0131a8db90b4a77560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:09.598688Z","signature_b64":"99PooX9J9hHttmYwDdzfxeQN+CXkDE47ugf7R6Ahk8R8rhNqPfXbtZ4DIi964OoaVx+fJFqEyK5Viu2El4TQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1abe33b7e9a72113d43cade740f7cc2d8ce0f62355bc97cec7b1f15af0debcca","last_reissued_at":"2026-07-05T02:11:09.598177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:09.598177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-free Stochastic Optimization of Variationally Coherent Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"D\\'avid P\\'al, Francesco Orabona","submitted_at":"2021-01-30T15:05:34Z","abstract_excerpt":"We design and analyze an algorithm for first-order stochastic optimization of a large class of functions on $\\mathbb{R}^d$. In particular, we consider the \\emph{variationally coherent} functions which can be convex or non-convex. The iterates of our algorithm on variationally coherent functions converge almost surely to the global minimizer $\\boldsymbol{x}^*$. Additionally, the very same algorithm with the same hyperparameters, after $T$ iterations guarantees on convex functions that the expected suboptimality gap is bounded by $\\widetilde{O}(\\|\\boldsymbol{x}^* - \\boldsymbol{x}_0\\| T^{-1/2+\\ep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00236","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/2102.00236/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":"2102.00236","created_at":"2026-07-05T02:11:09.598236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.00236v1","created_at":"2026-07-05T02:11:09.598236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00236","created_at":"2026-07-05T02:11:09.598236+00:00"},{"alias_kind":"pith_short_12","alias_value":"DK7DHN7JU4QR","created_at":"2026-07-05T02:11:09.598236+00:00"},{"alias_kind":"pith_short_16","alias_value":"DK7DHN7JU4QRHVB4","created_at":"2026-07-05T02:11:09.598236+00:00"},{"alias_kind":"pith_short_8","alias_value":"DK7DHN7J","created_at":"2026-07-05T02:11:09.598236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24981","citing_title":"A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07841","citing_title":"Large-scale empirical tuning and comparison of default optimizers for variational inference","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00419","citing_title":"Parameter-Free and Group Conditional Online Conformal Prediction","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW","json":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW.json","graph_json":"https://pith.science/api/pith-number/DK7DHN7JU4QRHVB4VXTUB56MFW/graph.json","events_json":"https://pith.science/api/pith-number/DK7DHN7JU4QRHVB4VXTUB56MFW/events.json","paper":"https://pith.science/paper/DK7DHN7J"},"agent_actions":{"view_html":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW","download_json":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW.json","view_paper":"https://pith.science/paper/DK7DHN7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.00236&json=true","fetch_graph":"https://pith.science/api/pith-number/DK7DHN7JU4QRHVB4VXTUB56MFW/graph.json","fetch_events":"https://pith.science/api/pith-number/DK7DHN7JU4QRHVB4VXTUB56MFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW/action/storage_attestation","attest_author":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW/action/author_attestation","sign_citation":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW/action/citation_signature","submit_replication":"https://pith.science/pith/DK7DHN7JU4QRHVB4VXTUB56MFW/action/replication_record"}},"created_at":"2026-07-05T02:11:09.598236+00:00","updated_at":"2026-07-05T02:11:09.598236+00:00"}