{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3ELUWOFSV7WXZ5UCX5GIKHU2TG","short_pith_number":"pith:3ELUWOFS","schema_version":"1.0","canonical_sha256":"d9174b38b2afed7cf682bf4c851e9a9997543f4e193e70bd6b2ca439636b4de4","source":{"kind":"arxiv","id":"2001.08437","version":2},"attestation_state":"computed","paper":{"title":"Multi-objective Neural Architecture Search via Non-stationary Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fengwei Zhou, George Trimponias, Zewei Chen, Zhenguo Li","submitted_at":"2020-01-23T10:37:11Z","abstract_excerpt":"Multi-objective Neural Architecture Search (NAS) aims to discover novel architectures in the presence of multiple conflicting objectives. Despite recent progress, the problem of approximating the full Pareto front accurately and efficiently remains challenging. In this work, we explore the novel reinforcement learning (RL) based paradigm of non-stationary policy gradient (NPG). NPG utilizes a non-stationary reward function, and encourages a continuous adaptation of the policy to capture the entire Pareto front efficiently. We introduce two novel reward functions with elements from the dominant"},"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":"2001.08437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-23T10:37:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a297ee3c78d67d95bbb82d747c8d0c79bbb593a236cb905950b78aa98954f304","abstract_canon_sha256":"3a51fad9164fdbaa25c0fc3f2f49ed1cc79a366e131e7f7014131e6bede6f708"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:30.511918Z","signature_b64":"/x0br9r76trGwjxZMrujg05hFAdADcQtEQ2+FcPA/2Z1UQhykQz8nLvCAWRHwC4bNcnW3yOdmpldnw+PqiVgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9174b38b2afed7cf682bf4c851e9a9997543f4e193e70bd6b2ca439636b4de4","last_reissued_at":"2026-07-05T00:37:30.511500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:30.511500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-objective Neural Architecture Search via Non-stationary Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fengwei Zhou, George Trimponias, Zewei Chen, Zhenguo Li","submitted_at":"2020-01-23T10:37:11Z","abstract_excerpt":"Multi-objective Neural Architecture Search (NAS) aims to discover novel architectures in the presence of multiple conflicting objectives. Despite recent progress, the problem of approximating the full Pareto front accurately and efficiently remains challenging. In this work, we explore the novel reinforcement learning (RL) based paradigm of non-stationary policy gradient (NPG). NPG utilizes a non-stationary reward function, and encourages a continuous adaptation of the policy to capture the entire Pareto front efficiently. We introduce two novel reward functions with elements from the dominant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08437","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/2001.08437/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":"2001.08437","created_at":"2026-07-05T00:37:30.511558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.08437v2","created_at":"2026-07-05T00:37:30.511558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08437","created_at":"2026-07-05T00:37:30.511558+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ELUWOFSV7WX","created_at":"2026-07-05T00:37:30.511558+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ELUWOFSV7WXZ5UC","created_at":"2026-07-05T00:37:30.511558+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ELUWOFS","created_at":"2026-07-05T00:37:30.511558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09707","citing_title":"Adaptive Data Harvesting for Efficient Neural Network Learning with Universal Constraints","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG","json":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG.json","graph_json":"https://pith.science/api/pith-number/3ELUWOFSV7WXZ5UCX5GIKHU2TG/graph.json","events_json":"https://pith.science/api/pith-number/3ELUWOFSV7WXZ5UCX5GIKHU2TG/events.json","paper":"https://pith.science/paper/3ELUWOFS"},"agent_actions":{"view_html":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG","download_json":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG.json","view_paper":"https://pith.science/paper/3ELUWOFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.08437&json=true","fetch_graph":"https://pith.science/api/pith-number/3ELUWOFSV7WXZ5UCX5GIKHU2TG/graph.json","fetch_events":"https://pith.science/api/pith-number/3ELUWOFSV7WXZ5UCX5GIKHU2TG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG/action/storage_attestation","attest_author":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG/action/author_attestation","sign_citation":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG/action/citation_signature","submit_replication":"https://pith.science/pith/3ELUWOFSV7WXZ5UCX5GIKHU2TG/action/replication_record"}},"created_at":"2026-07-05T00:37:30.511558+00:00","updated_at":"2026-07-05T00:37:30.511558+00:00"}