{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VWCKQYWYMFQJL2KBSPLQPOYMXT","short_pith_number":"pith:VWCKQYWY","schema_version":"1.0","canonical_sha256":"ad84a862d8616095e94193d707bb0cbcd0688715d5cd3673dd17b5eead86ca14","source":{"kind":"arxiv","id":"1710.05270","version":1},"attestation_state":"computed","paper":{"title":"Learning Infinite RBMs with Frank-Wolfe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Ihler, Qiang Liu, Wei Ping","submitted_at":"2017-10-15T03:38:32Z","abstract_excerpt":"In this work, we propose an infinite restricted Boltzmann machine~(RBM), whose maximum likelihood estimation~(MLE) corresponds to a constrained convex optimization. We consider the Frank-Wolfe algorithm to solve the program, which provides a sparse solution that can be interpreted as inserting a hidden unit at each iteration, so that the optimization process takes the form of a sequence of finite models of increasing complexity. As a side benefit, this can be used to easily and efficiently identify an appropriate number of hidden units during the optimization. The resulting model can also be u"},"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":"1710.05270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T03:38:32Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d2fe80ae75939931b12ffb0fb76a08b8fa92c76624e6de7e5e2da899dca13489","abstract_canon_sha256":"fe9053a4a49aff45e8c6babad9f6543b37f6606e40988a2a34ac7a41ea17d76d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:53.795896Z","signature_b64":"Y/U0zlT9xhAtAhY79Y9Qrh3tuC0fIdSLcATBgdVQQHPhVETpONeMyf4HqgkgnAdpn2yovIFjpLmNqv/JkvhpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad84a862d8616095e94193d707bb0cbcd0688715d5cd3673dd17b5eead86ca14","last_reissued_at":"2026-05-18T00:32:53.795214Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:53.795214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Infinite RBMs with Frank-Wolfe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Ihler, Qiang Liu, Wei Ping","submitted_at":"2017-10-15T03:38:32Z","abstract_excerpt":"In this work, we propose an infinite restricted Boltzmann machine~(RBM), whose maximum likelihood estimation~(MLE) corresponds to a constrained convex optimization. We consider the Frank-Wolfe algorithm to solve the program, which provides a sparse solution that can be interpreted as inserting a hidden unit at each iteration, so that the optimization process takes the form of a sequence of finite models of increasing complexity. As a side benefit, this can be used to easily and efficiently identify an appropriate number of hidden units during the optimization. The resulting model can also be u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.05270","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":"1710.05270","created_at":"2026-05-18T00:32:53.795337+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.05270v1","created_at":"2026-05-18T00:32:53.795337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.05270","created_at":"2026-05-18T00:32:53.795337+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWCKQYWYMFQJ","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWCKQYWYMFQJL2KB","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWCKQYWY","created_at":"2026-05-18T12:31:49.984773+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/VWCKQYWYMFQJL2KBSPLQPOYMXT","json":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT.json","graph_json":"https://pith.science/api/pith-number/VWCKQYWYMFQJL2KBSPLQPOYMXT/graph.json","events_json":"https://pith.science/api/pith-number/VWCKQYWYMFQJL2KBSPLQPOYMXT/events.json","paper":"https://pith.science/paper/VWCKQYWY"},"agent_actions":{"view_html":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT","download_json":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT.json","view_paper":"https://pith.science/paper/VWCKQYWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.05270&json=true","fetch_graph":"https://pith.science/api/pith-number/VWCKQYWYMFQJL2KBSPLQPOYMXT/graph.json","fetch_events":"https://pith.science/api/pith-number/VWCKQYWYMFQJL2KBSPLQPOYMXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT/action/storage_attestation","attest_author":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT/action/author_attestation","sign_citation":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT/action/citation_signature","submit_replication":"https://pith.science/pith/VWCKQYWYMFQJL2KBSPLQPOYMXT/action/replication_record"}},"created_at":"2026-05-18T00:32:53.795337+00:00","updated_at":"2026-05-18T00:32:53.795337+00:00"}