{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PNBI7VW7BNVDWWNZRKUOFKCKB6","short_pith_number":"pith:PNBI7VW7","schema_version":"1.0","canonical_sha256":"7b428fd6df0b6a3b59b98aa8e2a84a0f820843f7c6230f0d0f903e8e09572782","source":{"kind":"arxiv","id":"2002.09434","version":2},"attestation_state":"computed","paper":{"title":"Few-Shot Learning via Learning the Representation, Provably","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Qi Lei, Sham M. Kakade, Simon S. Du, Wei Hu","submitted_at":"2020-02-21T17:30:00Z","abstract_excerpt":"This paper studies few-shot learning via representation learning, where one uses $T$ source tasks with $n_1$ data per task to learn a representation in order to reduce the sample complexity of a target task for which there is only $n_2 (\\ll n_1)$ data. Specifically, we focus on the setting where there exists a good \\emph{common representation} between source and target, and our goal is to understand how much of a sample size reduction is possible. First, we study the setting where this common representation is low-dimensional and provide a fast rate of $O\\left(\\frac{\\mathcal{C}\\left(\\Phi\\right"},"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":"2002.09434","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-21T17:30:00Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"75b655c902a10dee01251996ad99ba9c005ee1ba7b0c65a69adf0d418c8ae32c","abstract_canon_sha256":"0440e4da59f2a089559da3a66871c7e48b4ca39eb657a784c3ce74009d0c9df8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:19.349484Z","signature_b64":"9bV6fI4jF9hjRd5vyT7eM/6yKFzNrjtkYtBzH3T6nVirdSMIPOYJUT2ln6gRVDbXggS6fx9dfttbCab6M5c6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b428fd6df0b6a3b59b98aa8e2a84a0f820843f7c6230f0d0f903e8e09572782","last_reissued_at":"2026-07-05T02:27:19.348943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:19.348943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Learning via Learning the Representation, Provably","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Qi Lei, Sham M. Kakade, Simon S. Du, Wei Hu","submitted_at":"2020-02-21T17:30:00Z","abstract_excerpt":"This paper studies few-shot learning via representation learning, where one uses $T$ source tasks with $n_1$ data per task to learn a representation in order to reduce the sample complexity of a target task for which there is only $n_2 (\\ll n_1)$ data. Specifically, we focus on the setting where there exists a good \\emph{common representation} between source and target, and our goal is to understand how much of a sample size reduction is possible. First, we study the setting where this common representation is low-dimensional and provide a fast rate of $O\\left(\\frac{\\mathcal{C}\\left(\\Phi\\right"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09434","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/2002.09434/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":"2002.09434","created_at":"2026-07-05T02:27:19.349006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09434v2","created_at":"2026-07-05T02:27:19.349006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09434","created_at":"2026-07-05T02:27:19.349006+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNBI7VW7BNVD","created_at":"2026-07-05T02:27:19.349006+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNBI7VW7BNVDWWNZ","created_at":"2026-07-05T02:27:19.349006+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNBI7VW7","created_at":"2026-07-05T02:27:19.349006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.23448","citing_title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6","json":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6.json","graph_json":"https://pith.science/api/pith-number/PNBI7VW7BNVDWWNZRKUOFKCKB6/graph.json","events_json":"https://pith.science/api/pith-number/PNBI7VW7BNVDWWNZRKUOFKCKB6/events.json","paper":"https://pith.science/paper/PNBI7VW7"},"agent_actions":{"view_html":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6","download_json":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6.json","view_paper":"https://pith.science/paper/PNBI7VW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09434&json=true","fetch_graph":"https://pith.science/api/pith-number/PNBI7VW7BNVDWWNZRKUOFKCKB6/graph.json","fetch_events":"https://pith.science/api/pith-number/PNBI7VW7BNVDWWNZRKUOFKCKB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6/action/storage_attestation","attest_author":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6/action/author_attestation","sign_citation":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6/action/citation_signature","submit_replication":"https://pith.science/pith/PNBI7VW7BNVDWWNZRKUOFKCKB6/action/replication_record"}},"created_at":"2026-07-05T02:27:19.349006+00:00","updated_at":"2026-07-05T02:27:19.349006+00:00"}