{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AA4H3G26IKXQAJT5J2XATMCGR3","short_pith_number":"pith:AA4H3G26","schema_version":"1.0","canonical_sha256":"00387d9b5e42af00267d4eae09b0468eeb71d06ac8eff26982f8db4ff03b980a","source":{"kind":"arxiv","id":"2002.05826","version":1},"attestation_state":"computed","paper":{"title":"Statistical Learning with Conditional Value at Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tasuku Soma, Yuichi Yoshida","submitted_at":"2020-02-14T00:58:34Z","abstract_excerpt":"We propose a risk-averse statistical learning framework wherein the performance of a learning algorithm is evaluated by the conditional value-at-risk (CVaR) of losses rather than the expected loss. We devise algorithms based on stochastic gradient descent for this framework. While existing studies of CVaR optimization require direct access to the underlying distribution, our algorithms make a weaker assumption that only i.i.d.\\ samples are given. For convex and Lipschitz loss functions, we show that our algorithm has $O(1/\\sqrt{n})$-convergence to the optimal CVaR, where $n$ is the number of s"},"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":"2002.05826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-14T00:58:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"52e8cf6eeba93ba11697d35cca40832ec90ee4a0889c86f849f37ca1d01c3281","abstract_canon_sha256":"a9ca9bd3e9cda71a15fff31962571bcb19044cc2d1738af3c4735b5e53140910"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:47.016230Z","signature_b64":"R7H2w2G5BxXKjomlhXnSo+i82NJgUzJZdJr7EVEmAnqbcwX8OYPQvjPqId91FrsElQrHoE/KntnT4166xl3pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00387d9b5e42af00267d4eae09b0468eeb71d06ac8eff26982f8db4ff03b980a","last_reissued_at":"2026-07-05T00:40:47.015756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:47.015756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Learning with Conditional Value at Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tasuku Soma, Yuichi Yoshida","submitted_at":"2020-02-14T00:58:34Z","abstract_excerpt":"We propose a risk-averse statistical learning framework wherein the performance of a learning algorithm is evaluated by the conditional value-at-risk (CVaR) of losses rather than the expected loss. We devise algorithms based on stochastic gradient descent for this framework. While existing studies of CVaR optimization require direct access to the underlying distribution, our algorithms make a weaker assumption that only i.i.d.\\ samples are given. For convex and Lipschitz loss functions, we show that our algorithm has $O(1/\\sqrt{n})$-convergence to the optimal CVaR, where $n$ is the number of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05826","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/2002.05826/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":"2002.05826","created_at":"2026-07-05T00:40:47.015815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05826v1","created_at":"2026-07-05T00:40:47.015815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05826","created_at":"2026-07-05T00:40:47.015815+00:00"},{"alias_kind":"pith_short_12","alias_value":"AA4H3G26IKXQ","created_at":"2026-07-05T00:40:47.015815+00:00"},{"alias_kind":"pith_short_16","alias_value":"AA4H3G26IKXQAJT5","created_at":"2026-07-05T00:40:47.015815+00:00"},{"alias_kind":"pith_short_8","alias_value":"AA4H3G26","created_at":"2026-07-05T00:40:47.015815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12519","citing_title":"Instantiating Bayesian CVaR lower bounds in Interactive Decision Making Problems","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18546","citing_title":"Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3","json":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3.json","graph_json":"https://pith.science/api/pith-number/AA4H3G26IKXQAJT5J2XATMCGR3/graph.json","events_json":"https://pith.science/api/pith-number/AA4H3G26IKXQAJT5J2XATMCGR3/events.json","paper":"https://pith.science/paper/AA4H3G26"},"agent_actions":{"view_html":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3","download_json":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3.json","view_paper":"https://pith.science/paper/AA4H3G26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05826&json=true","fetch_graph":"https://pith.science/api/pith-number/AA4H3G26IKXQAJT5J2XATMCGR3/graph.json","fetch_events":"https://pith.science/api/pith-number/AA4H3G26IKXQAJT5J2XATMCGR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3/action/storage_attestation","attest_author":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3/action/author_attestation","sign_citation":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3/action/citation_signature","submit_replication":"https://pith.science/pith/AA4H3G26IKXQAJT5J2XATMCGR3/action/replication_record"}},"created_at":"2026-07-05T00:40:47.015815+00:00","updated_at":"2026-07-05T00:40:47.015815+00:00"}