{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ISAYYFZCPFNWWLRFN4IQOYFCUY","short_pith_number":"pith:ISAYYFZC","schema_version":"1.0","canonical_sha256":"44818c1722795b6b2e256f110760a2a628f5bc1f942270259a7ae9e701d27c02","source":{"kind":"arxiv","id":"1807.09089","version":2},"attestation_state":"computed","paper":{"title":"Decision Variance in Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexis Boukouvalas, Qing Zhao, Sattar Vakili","submitted_at":"2018-07-24T13:20:49Z","abstract_excerpt":"Online learning has traditionally focused on the expected rewards. In this paper, a risk-averse online learning problem under the performance measure of the mean-variance of the rewards is studied. Both the bandit and full information settings are considered. The performance of several existing policies is analyzed, and new fundamental limitations on risk-averse learning is established. In particular, it is shown that although a logarithmic distribution-dependent regret in time $T$ is achievable (similar to the risk-neutral problem), the worst-case (i.e. minimax) regret is lower bounded by $\\O"},"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":"1807.09089","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-24T13:20:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89cc5628b891edb84ba850263bcb5c0f7af8150bd608012a96b25bf9d3321185","abstract_canon_sha256":"5aa45256bce912932ccee2be5a9600d1aa86a238ef848d0132bf8d0c05bb18f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:19.668539Z","signature_b64":"FCprMz/fIj6j4PMSd/VH91yCP85t5bHqiC8S2rsmJd2WxXjH75cxSYjeAHzmu0lzCzkkz0K1DREb2iajw6GdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44818c1722795b6b2e256f110760a2a628f5bc1f942270259a7ae9e701d27c02","last_reissued_at":"2026-05-17T23:51:19.668079Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:19.668079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decision Variance in Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexis Boukouvalas, Qing Zhao, Sattar Vakili","submitted_at":"2018-07-24T13:20:49Z","abstract_excerpt":"Online learning has traditionally focused on the expected rewards. In this paper, a risk-averse online learning problem under the performance measure of the mean-variance of the rewards is studied. Both the bandit and full information settings are considered. The performance of several existing policies is analyzed, and new fundamental limitations on risk-averse learning is established. In particular, it is shown that although a logarithmic distribution-dependent regret in time $T$ is achievable (similar to the risk-neutral problem), the worst-case (i.e. minimax) regret is lower bounded by $\\O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09089","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":""},"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":"1807.09089","created_at":"2026-05-17T23:51:19.668140+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09089v2","created_at":"2026-05-17T23:51:19.668140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09089","created_at":"2026-05-17T23:51:19.668140+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISAYYFZCPFNW","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISAYYFZCPFNWWLRF","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISAYYFZC","created_at":"2026-05-18T12:32:31.084164+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/ISAYYFZCPFNWWLRFN4IQOYFCUY","json":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY.json","graph_json":"https://pith.science/api/pith-number/ISAYYFZCPFNWWLRFN4IQOYFCUY/graph.json","events_json":"https://pith.science/api/pith-number/ISAYYFZCPFNWWLRFN4IQOYFCUY/events.json","paper":"https://pith.science/paper/ISAYYFZC"},"agent_actions":{"view_html":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY","download_json":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY.json","view_paper":"https://pith.science/paper/ISAYYFZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09089&json=true","fetch_graph":"https://pith.science/api/pith-number/ISAYYFZCPFNWWLRFN4IQOYFCUY/graph.json","fetch_events":"https://pith.science/api/pith-number/ISAYYFZCPFNWWLRFN4IQOYFCUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY/action/storage_attestation","attest_author":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY/action/author_attestation","sign_citation":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY/action/citation_signature","submit_replication":"https://pith.science/pith/ISAYYFZCPFNWWLRFN4IQOYFCUY/action/replication_record"}},"created_at":"2026-05-17T23:51:19.668140+00:00","updated_at":"2026-05-17T23:51:19.668140+00:00"}