{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7QU3ELIX6L3BACSORCU552QUQA","short_pith_number":"pith:7QU3ELIX","schema_version":"1.0","canonical_sha256":"fc29b22d17f2f6100a4e88a9deea14803a810bd24307d600abe91fb12cc0efb5","source":{"kind":"arxiv","id":"1812.10244","version":2},"attestation_state":"computed","paper":{"title":"Towards a Theoretical Understanding of Hashing-Based Neural Nets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Yibo Lin, Zhao Song","submitted_at":"2018-12-26T06:45:12Z","abstract_excerpt":"Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limited machines. Despite many efforts in this area, there were no rigorous theoretical guarantees on why existing neural net compression methods should work. In this paper, we provide provable guarantees on some hashing-based parameter reduction methods in neural nets. First, we introduce a neural net compression scheme based on random linear sketching (which is usually implemented efficiently via hashing), and 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":"1812.10244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-12-26T06:45:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0a0d862a4680ef5b1127e106d9dbc5ec056a9dea051015257bc6d65e950cd7c1","abstract_canon_sha256":"56b8332a04c167ba2b57b4b2421e133f6c09a43e67209a9704c2cd73152e03ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:51.187737Z","signature_b64":"ga1sJm1Rn9Hbb+SXOZB09G30HOXpgfwdTR4eV+ttIlI/oR5PGdyZfZl3SDPKuTN+/dy+Tx1j+ZejhcCpz9LYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc29b22d17f2f6100a4e88a9deea14803a810bd24307d600abe91fb12cc0efb5","last_reissued_at":"2026-05-17T23:52:51.186847Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:51.186847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards a Theoretical Understanding of Hashing-Based Neural Nets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Yibo Lin, Zhao Song","submitted_at":"2018-12-26T06:45:12Z","abstract_excerpt":"Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limited machines. Despite many efforts in this area, there were no rigorous theoretical guarantees on why existing neural net compression methods should work. In this paper, we provide provable guarantees on some hashing-based parameter reduction methods in neural nets. First, we introduce a neural net compression scheme based on random linear sketching (which is usually implemented efficiently via hashing), and show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10244","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":""},"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":"1812.10244","created_at":"2026-05-17T23:52:51.187001+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10244v2","created_at":"2026-05-17T23:52:51.187001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10244","created_at":"2026-05-17T23:52:51.187001+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QU3ELIX6L3B","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QU3ELIX6L3BACSO","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QU3ELIX","created_at":"2026-05-18T12:32:11.075285+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/7QU3ELIX6L3BACSORCU552QUQA","json":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA.json","graph_json":"https://pith.science/api/pith-number/7QU3ELIX6L3BACSORCU552QUQA/graph.json","events_json":"https://pith.science/api/pith-number/7QU3ELIX6L3BACSORCU552QUQA/events.json","paper":"https://pith.science/paper/7QU3ELIX"},"agent_actions":{"view_html":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA","download_json":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA.json","view_paper":"https://pith.science/paper/7QU3ELIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10244&json=true","fetch_graph":"https://pith.science/api/pith-number/7QU3ELIX6L3BACSORCU552QUQA/graph.json","fetch_events":"https://pith.science/api/pith-number/7QU3ELIX6L3BACSORCU552QUQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA/action/storage_attestation","attest_author":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA/action/author_attestation","sign_citation":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA/action/citation_signature","submit_replication":"https://pith.science/pith/7QU3ELIX6L3BACSORCU552QUQA/action/replication_record"}},"created_at":"2026-05-17T23:52:51.187001+00:00","updated_at":"2026-05-17T23:52:51.187001+00:00"}