{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2PJBVLWPUANIA4DIBDRMJWNDUY","short_pith_number":"pith:2PJBVLWP","schema_version":"1.0","canonical_sha256":"d3d21aaecfa01a80706808e2c4d9a3a6019497fcaeef6665852785ce27da8725","source":{"kind":"arxiv","id":"1802.09732","version":1},"attestation_state":"computed","paper":{"title":"Online learning with kernel losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aldo Pacchiano, Niladri S. Chatterji, Peter L. Bartlett","submitted_at":"2018-02-27T06:07:54Z","abstract_excerpt":"We present a generalization of the adversarial linear bandits framework, where the underlying losses are kernel functions (with an associated reproducing kernel Hilbert space) rather than linear functions. We study a version of the exponential weights algorithm and bound its regret in this setting. Under conditions on the eigendecay of the kernel we provide a sharp characterization of the regret for this algorithm. When we have polynomial eigendecay $\\mu_j \\le \\mathcal{O}(j^{-\\beta})$, we find that the regret is bounded by $\\mathcal{R}_n \\le \\mathcal{O}(n^{\\beta/(2(\\beta-1))})$; while under th"},"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":"1802.09732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-27T06:07:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b9b1d7cb109d387f6e37393082e55acd872d6e37db3038bf17e5135610d5151c","abstract_canon_sha256":"ebc61c0a8721c91b16135e3d1141d6d26dbc1d3387ee9d965492a6bceb6367ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:30.240962Z","signature_b64":"X/0NH6hw5dHdBrYcOA3SlG94KP5MtZxrN3gEL7Mwp0/ZnHEZGhjguMnwLgrkmjhw1lSEgnlfuaepvs1KjNUPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3d21aaecfa01a80706808e2c4d9a3a6019497fcaeef6665852785ce27da8725","last_reissued_at":"2026-05-18T00:22:30.240276Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:30.240276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online learning with kernel losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aldo Pacchiano, Niladri S. Chatterji, Peter L. Bartlett","submitted_at":"2018-02-27T06:07:54Z","abstract_excerpt":"We present a generalization of the adversarial linear bandits framework, where the underlying losses are kernel functions (with an associated reproducing kernel Hilbert space) rather than linear functions. We study a version of the exponential weights algorithm and bound its regret in this setting. Under conditions on the eigendecay of the kernel we provide a sharp characterization of the regret for this algorithm. When we have polynomial eigendecay $\\mu_j \\le \\mathcal{O}(j^{-\\beta})$, we find that the regret is bounded by $\\mathcal{R}_n \\le \\mathcal{O}(n^{\\beta/(2(\\beta-1))})$; while under th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09732","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":""},"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":"1802.09732","created_at":"2026-05-18T00:22:30.240397+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09732v1","created_at":"2026-05-18T00:22:30.240397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09732","created_at":"2026-05-18T00:22:30.240397+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PJBVLWPUANI","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PJBVLWPUANIA4DI","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PJBVLWP","created_at":"2026-05-18T12:32:02.567920+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/2PJBVLWPUANIA4DIBDRMJWNDUY","json":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY.json","graph_json":"https://pith.science/api/pith-number/2PJBVLWPUANIA4DIBDRMJWNDUY/graph.json","events_json":"https://pith.science/api/pith-number/2PJBVLWPUANIA4DIBDRMJWNDUY/events.json","paper":"https://pith.science/paper/2PJBVLWP"},"agent_actions":{"view_html":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY","download_json":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY.json","view_paper":"https://pith.science/paper/2PJBVLWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09732&json=true","fetch_graph":"https://pith.science/api/pith-number/2PJBVLWPUANIA4DIBDRMJWNDUY/graph.json","fetch_events":"https://pith.science/api/pith-number/2PJBVLWPUANIA4DIBDRMJWNDUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY/action/storage_attestation","attest_author":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY/action/author_attestation","sign_citation":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY/action/citation_signature","submit_replication":"https://pith.science/pith/2PJBVLWPUANIA4DIBDRMJWNDUY/action/replication_record"}},"created_at":"2026-05-18T00:22:30.240397+00:00","updated_at":"2026-05-18T00:22:30.240397+00:00"}