{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WNYNCNFQLC5JLLRXIT7W3OPELX","short_pith_number":"pith:WNYNCNFQ","schema_version":"1.0","canonical_sha256":"b370d134b058ba95ae3744ff6db9e45ddded3868adae435022702d08bca40454","source":{"kind":"arxiv","id":"1907.08653","version":1},"attestation_state":"computed","paper":{"title":"Surfing: Iterative optimization over incrementally trained deep networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ganlin Song, John Lafferty, Zhou Fan","submitted_at":"2019-07-19T19:16:04Z","abstract_excerpt":"We investigate a sequential optimization procedure to minimize the empirical risk functional $f_{\\hat\\theta}(x) = \\frac{1}{2}\\|G_{\\hat\\theta}(x) - y\\|^2$ for certain families of deep networks $G_{\\theta}(x)$. The approach is to optimize a sequence of objective functions that use network parameters obtained during different stages of the training process. When initialized with random parameters $\\theta_0$, we show that the objective $f_{\\theta_0}(x)$ is \"nice'' and easy to optimize with gradient descent. As learning is carried out, we obtain a sequence of generative networks $x \\mapsto G_{\\thet"},"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":"1907.08653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-19T19:16:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b42763188db00282d92f853a9fca37e62a900fd78f675eb858c20378bae03e3f","abstract_canon_sha256":"de6ce443733f7472438baa977e054ab12a303f4526a7db0ba8425397d3c63cdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:08.281237Z","signature_b64":"O06WruUYE3hLQSUliAun5XiA8KuvtZLBkBl2shucssNphdxvsCc0nsU3ruA0F4R3AQUEDkuCHy2sP8ecFPnqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b370d134b058ba95ae3744ff6db9e45ddded3868adae435022702d08bca40454","last_reissued_at":"2026-05-17T23:40:08.280450Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:08.280450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surfing: Iterative optimization over incrementally trained deep networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ganlin Song, John Lafferty, Zhou Fan","submitted_at":"2019-07-19T19:16:04Z","abstract_excerpt":"We investigate a sequential optimization procedure to minimize the empirical risk functional $f_{\\hat\\theta}(x) = \\frac{1}{2}\\|G_{\\hat\\theta}(x) - y\\|^2$ for certain families of deep networks $G_{\\theta}(x)$. The approach is to optimize a sequence of objective functions that use network parameters obtained during different stages of the training process. When initialized with random parameters $\\theta_0$, we show that the objective $f_{\\theta_0}(x)$ is \"nice'' and easy to optimize with gradient descent. As learning is carried out, we obtain a sequence of generative networks $x \\mapsto G_{\\thet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08653","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":""},"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":"1907.08653","created_at":"2026-05-17T23:40:08.280595+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.08653v1","created_at":"2026-05-17T23:40:08.280595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08653","created_at":"2026-05-17T23:40:08.280595+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNYNCNFQLC5J","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNYNCNFQLC5JLLRX","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNYNCNFQ","created_at":"2026-05-18T12:33:30.264802+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/WNYNCNFQLC5JLLRXIT7W3OPELX","json":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX.json","graph_json":"https://pith.science/api/pith-number/WNYNCNFQLC5JLLRXIT7W3OPELX/graph.json","events_json":"https://pith.science/api/pith-number/WNYNCNFQLC5JLLRXIT7W3OPELX/events.json","paper":"https://pith.science/paper/WNYNCNFQ"},"agent_actions":{"view_html":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX","download_json":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX.json","view_paper":"https://pith.science/paper/WNYNCNFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.08653&json=true","fetch_graph":"https://pith.science/api/pith-number/WNYNCNFQLC5JLLRXIT7W3OPELX/graph.json","fetch_events":"https://pith.science/api/pith-number/WNYNCNFQLC5JLLRXIT7W3OPELX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX/action/storage_attestation","attest_author":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX/action/author_attestation","sign_citation":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX/action/citation_signature","submit_replication":"https://pith.science/pith/WNYNCNFQLC5JLLRXIT7W3OPELX/action/replication_record"}},"created_at":"2026-05-17T23:40:08.280595+00:00","updated_at":"2026-05-17T23:40:08.280595+00:00"}