{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RGNKDZVWTJWM76IDXLPLPA3MTE","short_pith_number":"pith:RGNKDZVW","schema_version":"1.0","canonical_sha256":"899aa1e6b69a6ccff903badeb7836c993da5b65bda6dc2ea47c8bb03df5972c5","source":{"kind":"arxiv","id":"1608.07892","version":3},"attestation_state":"computed","paper":{"title":"Optimizing Recurrent Neural Networks Architectures under Time Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changshui Zhang, Junqi Jin, Kun Fu, Nan Jiang, Ziang Yan","submitted_at":"2016-08-29T02:14:48Z","abstract_excerpt":"Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert the discrete optimization into a subset selection problem. By novel transformations, the objective function becomes submodular and constraint becomes supermodular. A greedy algorithm with bounds is suggested to solve the transformed problem. And we show how transformations influence the bounds. To speed up optimization, surrogate functions are proposed which balance exploration and exploitation. Experiments show that"},"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":"1608.07892","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-29T02:14:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7d1253f5fea1260a176306ed177285a445adcbbfee9725d2108ce48aef7afa0f","abstract_canon_sha256":"1bc0e9738b54078ec22df85bf263c4d6fc2cd268880519dd532295b83bff0ed6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:53.015723Z","signature_b64":"aXE3VUYETNYCCbIlfsIpaVn8wtZuBYRESo5aKCsZMDOHg4jGWHDvpnrxlwuRKTJj7fwqnqt0MiXw74LFMju6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"899aa1e6b69a6ccff903badeb7836c993da5b65bda6dc2ea47c8bb03df5972c5","last_reissued_at":"2026-05-18T00:22:53.015286Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:53.015286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Recurrent Neural Networks Architectures under Time Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changshui Zhang, Junqi Jin, Kun Fu, Nan Jiang, Ziang Yan","submitted_at":"2016-08-29T02:14:48Z","abstract_excerpt":"Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert the discrete optimization into a subset selection problem. By novel transformations, the objective function becomes submodular and constraint becomes supermodular. A greedy algorithm with bounds is suggested to solve the transformed problem. And we show how transformations influence the bounds. To speed up optimization, surrogate functions are proposed which balance exploration and exploitation. Experiments show that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.07892","kind":"arxiv","version":3},"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":"1608.07892","created_at":"2026-05-18T00:22:53.015367+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.07892v3","created_at":"2026-05-18T00:22:53.015367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.07892","created_at":"2026-05-18T00:22:53.015367+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGNKDZVWTJWM","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGNKDZVWTJWM76ID","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGNKDZVW","created_at":"2026-05-18T12:30:41.710351+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/RGNKDZVWTJWM76IDXLPLPA3MTE","json":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE.json","graph_json":"https://pith.science/api/pith-number/RGNKDZVWTJWM76IDXLPLPA3MTE/graph.json","events_json":"https://pith.science/api/pith-number/RGNKDZVWTJWM76IDXLPLPA3MTE/events.json","paper":"https://pith.science/paper/RGNKDZVW"},"agent_actions":{"view_html":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE","download_json":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE.json","view_paper":"https://pith.science/paper/RGNKDZVW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.07892&json=true","fetch_graph":"https://pith.science/api/pith-number/RGNKDZVWTJWM76IDXLPLPA3MTE/graph.json","fetch_events":"https://pith.science/api/pith-number/RGNKDZVWTJWM76IDXLPLPA3MTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE/action/storage_attestation","attest_author":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE/action/author_attestation","sign_citation":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE/action/citation_signature","submit_replication":"https://pith.science/pith/RGNKDZVWTJWM76IDXLPLPA3MTE/action/replication_record"}},"created_at":"2026-05-18T00:22:53.015367+00:00","updated_at":"2026-05-18T00:22:53.015367+00:00"}