{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RXTIG2HBDEFSUNBEZ4BRHWCDNC","short_pith_number":"pith:RXTIG2HB","schema_version":"1.0","canonical_sha256":"8de68368e1190b2a3424cf0313d84368a7d514f1d911072783a10f4cd7f82a81","source":{"kind":"arxiv","id":"2109.12425","version":1},"attestation_state":"computed","paper":{"title":"L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Di Niu, Fred X. Han, Keith G. Mills, Linglong Kong, Mohammad Salameh, Seyed Saeed Changiz Rezaei, Shangling Jui, Shuo Lian, Wei Lu","submitted_at":"2021-09-25T19:26:30Z","abstract_excerpt":"Neural architecture search (NAS) has achieved remarkable results in deep neural network design. Differentiable architecture search converts the search over discrete architectures into a hyperparameter optimization problem which can be solved by gradient descent. However, questions have been raised regarding the effectiveness and generalizability of gradient methods for solving non-convex architecture hyperparameter optimization problems. In this paper, we propose L$^{2}$NAS, which learns to intelligently optimize and update architecture hyperparameters via an actor neural network based on the "},"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":"2109.12425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-25T19:26:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0532fc9f3cc78aeb8b65543acc660120f97f75f5cd4822adcca89928819a182b","abstract_canon_sha256":"0e131baa08afb140131da4507c27a909d0973a21623d811a5c0d7947c7ceedde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:20.574063Z","signature_b64":"AscpevFIw73mFjK7ZVDL7GNaiA7JZnLw3GROWMynNOYl5emH0p5TcEkLEfy/uhgcjKUpb6PdnFobEb9GND6hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de68368e1190b2a3424cf0313d84368a7d514f1d911072783a10f4cd7f82a81","last_reissued_at":"2026-07-05T03:17:20.573691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:20.573691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L$^{2}$NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Di Niu, Fred X. Han, Keith G. Mills, Linglong Kong, Mohammad Salameh, Seyed Saeed Changiz Rezaei, Shangling Jui, Shuo Lian, Wei Lu","submitted_at":"2021-09-25T19:26:30Z","abstract_excerpt":"Neural architecture search (NAS) has achieved remarkable results in deep neural network design. Differentiable architecture search converts the search over discrete architectures into a hyperparameter optimization problem which can be solved by gradient descent. However, questions have been raised regarding the effectiveness and generalizability of gradient methods for solving non-convex architecture hyperparameter optimization problems. In this paper, we propose L$^{2}$NAS, which learns to intelligently optimize and update architecture hyperparameters via an actor neural network based on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12425","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/2109.12425/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":"2109.12425","created_at":"2026-07-05T03:17:20.573734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.12425v1","created_at":"2026-07-05T03:17:20.573734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12425","created_at":"2026-07-05T03:17:20.573734+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXTIG2HBDEFS","created_at":"2026-07-05T03:17:20.573734+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXTIG2HBDEFSUNBE","created_at":"2026-07-05T03:17:20.573734+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXTIG2HB","created_at":"2026-07-05T03:17:20.573734+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/RXTIG2HBDEFSUNBEZ4BRHWCDNC","json":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC.json","graph_json":"https://pith.science/api/pith-number/RXTIG2HBDEFSUNBEZ4BRHWCDNC/graph.json","events_json":"https://pith.science/api/pith-number/RXTIG2HBDEFSUNBEZ4BRHWCDNC/events.json","paper":"https://pith.science/paper/RXTIG2HB"},"agent_actions":{"view_html":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC","download_json":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC.json","view_paper":"https://pith.science/paper/RXTIG2HB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.12425&json=true","fetch_graph":"https://pith.science/api/pith-number/RXTIG2HBDEFSUNBEZ4BRHWCDNC/graph.json","fetch_events":"https://pith.science/api/pith-number/RXTIG2HBDEFSUNBEZ4BRHWCDNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC/action/storage_attestation","attest_author":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC/action/author_attestation","sign_citation":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC/action/citation_signature","submit_replication":"https://pith.science/pith/RXTIG2HBDEFSUNBEZ4BRHWCDNC/action/replication_record"}},"created_at":"2026-07-05T03:17:20.573734+00:00","updated_at":"2026-07-05T03:17:20.573734+00:00"}