{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P2V7TQ4YJMMTZVVFNLRWEU32BB","short_pith_number":"pith:P2V7TQ4Y","schema_version":"1.0","canonical_sha256":"7eabf9c3984b193cd6a56ae362537a086d21f143736f5a0455715c0c127d5c73","source":{"kind":"arxiv","id":"1812.03372","version":3},"attestation_state":"computed","paper":{"title":"What is the Effect of Importance Weighting in Deep Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jonathon Byrd, Zachary C. Lipton","submitted_at":"2018-12-08T19:19:04Z","abstract_excerpt":"Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is well-characterized for low-capacity misspecified models, little is known about how it impacts over-parameterized, deep neural networks. This work is inspired by recent theoretical results showing that on (linearly) separable data, deep linear networks optimized by SGD learn weight-agnostic solutions, prompting us to ask, for realistic deep networks, for which man"},"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":"1812.03372","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-08T19:19:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c067c4f7fc019fc347c92745b58ebacf08b6a98f15bd9c51d34aeee7043270dd","abstract_canon_sha256":"0da25738da6839072c814ad2a3dc9d7e354329662c1ae938996e20726c7ffc73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:23.401135Z","signature_b64":"JPCczTyl+F5hIfVQAm7FW+pte+XmaKfeAJZL8uhYIoRRpgyICVEyTp0IayZayB94QL1gsWS/Jh+d8SEM8GivAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eabf9c3984b193cd6a56ae362537a086d21f143736f5a0455715c0c127d5c73","last_reissued_at":"2026-05-17T23:43:23.400568Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:23.400568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is the Effect of Importance Weighting in Deep Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jonathon Byrd, Zachary C. Lipton","submitted_at":"2018-12-08T19:19:04Z","abstract_excerpt":"Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is well-characterized for low-capacity misspecified models, little is known about how it impacts over-parameterized, deep neural networks. This work is inspired by recent theoretical results showing that on (linearly) separable data, deep linear networks optimized by SGD learn weight-agnostic solutions, prompting us to ask, for realistic deep networks, for which man"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.03372","kind":"arxiv","version":3},"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":"1812.03372","created_at":"2026-05-17T23:43:23.400661+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.03372v3","created_at":"2026-05-17T23:43:23.400661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.03372","created_at":"2026-05-17T23:43:23.400661+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2V7TQ4YJMMT","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2V7TQ4YJMMTZVVF","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2V7TQ4Y","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20771","citing_title":"Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB","json":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB.json","graph_json":"https://pith.science/api/pith-number/P2V7TQ4YJMMTZVVFNLRWEU32BB/graph.json","events_json":"https://pith.science/api/pith-number/P2V7TQ4YJMMTZVVFNLRWEU32BB/events.json","paper":"https://pith.science/paper/P2V7TQ4Y"},"agent_actions":{"view_html":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB","download_json":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB.json","view_paper":"https://pith.science/paper/P2V7TQ4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.03372&json=true","fetch_graph":"https://pith.science/api/pith-number/P2V7TQ4YJMMTZVVFNLRWEU32BB/graph.json","fetch_events":"https://pith.science/api/pith-number/P2V7TQ4YJMMTZVVFNLRWEU32BB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB/action/storage_attestation","attest_author":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB/action/author_attestation","sign_citation":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB/action/citation_signature","submit_replication":"https://pith.science/pith/P2V7TQ4YJMMTZVVFNLRWEU32BB/action/replication_record"}},"created_at":"2026-05-17T23:43:23.400661+00:00","updated_at":"2026-05-17T23:43:23.400661+00:00"}