{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZG4VAHTWRRSE3PJVSJV25J46VF","short_pith_number":"pith:ZG4VAHTW","schema_version":"1.0","canonical_sha256":"c9b9501e768c644dbd35926baea79ea9594e2d0f16fedb4b9cf3f37ed290fbbc","source":{"kind":"arxiv","id":"2007.12160","version":2},"attestation_state":"computed","paper":{"title":"Online Robust and Adaptive Learning from Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Atsushi Nitanda, Kenji Yamanishi, Shintaro Fukushima","submitted_at":"2020-07-23T17:49:04Z","abstract_excerpt":"In online learning from non-stationary data streams, it is necessary to learn robustly to outliers and to adapt quickly to changes in the underlying data generating mechanism. In this paper, we refer to the former attribute of online learning algorithms as robustness and to the latter as adaptivity. There is an obvious tradeoff between the two attributes. It is a fundamental issue to quantify and evaluate the tradeoff because it provides important information on the data generating mechanism. However, no previous work has considered the tradeoff quantitatively. We propose a novel algorithm cal"},"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":"2007.12160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-23T17:49:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12486bd7f94efb236023ad0f1221a126d35088b953130e2b4c86a1846a081d68","abstract_canon_sha256":"38a20b865e3356cf2bf6eec1039d134710d631d16aaea109a8f18dc03eefd76a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:44.851168Z","signature_b64":"cw77mZJOwI85iG40FZLt34yOr8d8i9YJ/l3QEsyX2vnBZUgimvFuBiZ+nmHn2qFBQ7bRDEjzMAac4ykhyclMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9b9501e768c644dbd35926baea79ea9594e2d0f16fedb4b9cf3f37ed290fbbc","last_reissued_at":"2026-07-05T03:17:44.850733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:44.850733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Robust and Adaptive Learning from Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Atsushi Nitanda, Kenji Yamanishi, Shintaro Fukushima","submitted_at":"2020-07-23T17:49:04Z","abstract_excerpt":"In online learning from non-stationary data streams, it is necessary to learn robustly to outliers and to adapt quickly to changes in the underlying data generating mechanism. In this paper, we refer to the former attribute of online learning algorithms as robustness and to the latter as adaptivity. There is an obvious tradeoff between the two attributes. It is a fundamental issue to quantify and evaluate the tradeoff because it provides important information on the data generating mechanism. However, no previous work has considered the tradeoff quantitatively. We propose a novel algorithm cal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12160","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.12160/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":"2007.12160","created_at":"2026-07-05T03:17:44.850801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12160v2","created_at":"2026-07-05T03:17:44.850801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12160","created_at":"2026-07-05T03:17:44.850801+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZG4VAHTWRRSE","created_at":"2026-07-05T03:17:44.850801+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZG4VAHTWRRSE3PJV","created_at":"2026-07-05T03:17:44.850801+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZG4VAHTW","created_at":"2026-07-05T03:17:44.850801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19647","citing_title":"CAdam: Confidence-Based Optimization for Online Learning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF","json":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF.json","graph_json":"https://pith.science/api/pith-number/ZG4VAHTWRRSE3PJVSJV25J46VF/graph.json","events_json":"https://pith.science/api/pith-number/ZG4VAHTWRRSE3PJVSJV25J46VF/events.json","paper":"https://pith.science/paper/ZG4VAHTW"},"agent_actions":{"view_html":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF","download_json":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF.json","view_paper":"https://pith.science/paper/ZG4VAHTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12160&json=true","fetch_graph":"https://pith.science/api/pith-number/ZG4VAHTWRRSE3PJVSJV25J46VF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZG4VAHTWRRSE3PJVSJV25J46VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF/action/storage_attestation","attest_author":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF/action/author_attestation","sign_citation":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF/action/citation_signature","submit_replication":"https://pith.science/pith/ZG4VAHTWRRSE3PJVSJV25J46VF/action/replication_record"}},"created_at":"2026-07-05T03:17:44.850801+00:00","updated_at":"2026-07-05T03:17:44.850801+00:00"}