{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:P5FZCUYMCBYOWFTX4NSSEMNIGE","short_pith_number":"pith:P5FZCUYM","schema_version":"1.0","canonical_sha256":"7f4b91530c1070eb1677e3652231a8312f8b877f80a6e18348198fb54e4d9c87","source":{"kind":"arxiv","id":"1705.11159","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Learning Rate Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Xu, Gang Wang, Tao Qin, Tie-Yan Liu","submitted_at":"2017-05-31T15:58:35Z","abstract_excerpt":"Stochastic gradient descent (SGD), which updates the model parameters by adding a local gradient times a learning rate at each step, is widely used in model training of machine learning algorithms such as neural networks. It is observed that the models trained by SGD are sensitive to learning rates and good learning rates are problem specific. We propose an algorithm to automatically learn learning rates using neural network based actor-critic methods from deep reinforcement learning (RL).In particular, we train a policy network called actor to decide the learning rate at each step during trai"},"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":"1705.11159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-31T15:58:35Z","cross_cats_sorted":[],"title_canon_sha256":"5290540a0ea2c0cba39a4dcf07248ac2d8f5ebe2647a69e55466bb052ba28c4e","abstract_canon_sha256":"7900ed35c572c60742e69a816bcccfe468a936912b0e22b73aba8b66da5cd657"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:19.087962Z","signature_b64":"nrS426mC3pVk99JZPhe129IO1IGnDdBnSThR6erf2+j7KTME0zCcfBMMGx/D3rtwuhtlvAF+38d1tGVC9f3CBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f4b91530c1070eb1677e3652231a8312f8b877f80a6e18348198fb54e4d9c87","last_reissued_at":"2026-05-18T00:43:19.087339Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:19.087339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Learning Rate Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chang Xu, Gang Wang, Tao Qin, Tie-Yan Liu","submitted_at":"2017-05-31T15:58:35Z","abstract_excerpt":"Stochastic gradient descent (SGD), which updates the model parameters by adding a local gradient times a learning rate at each step, is widely used in model training of machine learning algorithms such as neural networks. It is observed that the models trained by SGD are sensitive to learning rates and good learning rates are problem specific. We propose an algorithm to automatically learn learning rates using neural network based actor-critic methods from deep reinforcement learning (RL).In particular, we train a policy network called actor to decide the learning rate at each step during trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.11159","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":"1705.11159","created_at":"2026-05-18T00:43:19.087425+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.11159v1","created_at":"2026-05-18T00:43:19.087425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.11159","created_at":"2026-05-18T00:43:19.087425+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5FZCUYMCBYO","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5FZCUYMCBYOWFTX","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5FZCUYM","created_at":"2026-05-18T12:31:37.085036+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/P5FZCUYMCBYOWFTX4NSSEMNIGE","json":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE.json","graph_json":"https://pith.science/api/pith-number/P5FZCUYMCBYOWFTX4NSSEMNIGE/graph.json","events_json":"https://pith.science/api/pith-number/P5FZCUYMCBYOWFTX4NSSEMNIGE/events.json","paper":"https://pith.science/paper/P5FZCUYM"},"agent_actions":{"view_html":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE","download_json":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE.json","view_paper":"https://pith.science/paper/P5FZCUYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.11159&json=true","fetch_graph":"https://pith.science/api/pith-number/P5FZCUYMCBYOWFTX4NSSEMNIGE/graph.json","fetch_events":"https://pith.science/api/pith-number/P5FZCUYMCBYOWFTX4NSSEMNIGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE/action/storage_attestation","attest_author":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE/action/author_attestation","sign_citation":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE/action/citation_signature","submit_replication":"https://pith.science/pith/P5FZCUYMCBYOWFTX4NSSEMNIGE/action/replication_record"}},"created_at":"2026-05-18T00:43:19.087425+00:00","updated_at":"2026-05-18T00:43:19.087425+00:00"}