{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZJMPDFEKSCI5TIVYG7M6KCDMGX","short_pith_number":"pith:ZJMPDFEK","schema_version":"1.0","canonical_sha256":"ca58f1948a9091d9a2b837d9e5086c35d810f3054e7c051dccc459dbf0eb6194","source":{"kind":"arxiv","id":"1810.02309","version":3},"attestation_state":"computed","paper":{"title":"Learning Compressed Transforms with Low Displacement Rank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Anna T. Thomas, Atri Rudra, Christopher R\\'e, Tri Dao","submitted_at":"2018-10-04T16:44:16Z","abstract_excerpt":"The low displacement rank (LDR) framework for structured matrices represents a matrix through two displacement operators and a low-rank residual. Existing use of LDR matrices in deep learning has applied fixed displacement operators encoding forms of shift invariance akin to convolutions. We introduce a class of LDR matrices with more general displacement operators, and explicitly learn over both the operators and the low-rank component. This class generalizes several previous constructions while preserving compression and efficient computation. We prove bounds on the VC dimension of multi-lay"},"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":"1810.02309","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-04T16:44:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"681e723d4973d101a086f53cb8f23293166c306a58b4463834a23089acad964a","abstract_canon_sha256":"af07f442a738bb28aaca51095092b8e009c2496ce1823ab1bab691d3a804690e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:07.331048Z","signature_b64":"8F7EEqvdUBcJQow2HiymGQ3NBtAWnGerTh+VS66/t1kTRYX0ZLldnZ+EEsandNhguiFII5Mm/uvnOYvp/i/6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca58f1948a9091d9a2b837d9e5086c35d810f3054e7c051dccc459dbf0eb6194","last_reissued_at":"2026-05-17T23:57:07.330532Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:07.330532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Compressed Transforms with Low Displacement Rank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Anna T. Thomas, Atri Rudra, Christopher R\\'e, Tri Dao","submitted_at":"2018-10-04T16:44:16Z","abstract_excerpt":"The low displacement rank (LDR) framework for structured matrices represents a matrix through two displacement operators and a low-rank residual. Existing use of LDR matrices in deep learning has applied fixed displacement operators encoding forms of shift invariance akin to convolutions. We introduce a class of LDR matrices with more general displacement operators, and explicitly learn over both the operators and the low-rank component. This class generalizes several previous constructions while preserving compression and efficient computation. We prove bounds on the VC dimension of multi-lay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02309","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":"1810.02309","created_at":"2026-05-17T23:57:07.330615+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02309v3","created_at":"2026-05-17T23:57:07.330615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02309","created_at":"2026-05-17T23:57:07.330615+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJMPDFEKSCI5","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJMPDFEKSCI5TIVY","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJMPDFEK","created_at":"2026-05-18T12:33:07.085635+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/ZJMPDFEKSCI5TIVYG7M6KCDMGX","json":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX.json","graph_json":"https://pith.science/api/pith-number/ZJMPDFEKSCI5TIVYG7M6KCDMGX/graph.json","events_json":"https://pith.science/api/pith-number/ZJMPDFEKSCI5TIVYG7M6KCDMGX/events.json","paper":"https://pith.science/paper/ZJMPDFEK"},"agent_actions":{"view_html":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX","download_json":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX.json","view_paper":"https://pith.science/paper/ZJMPDFEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02309&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJMPDFEKSCI5TIVYG7M6KCDMGX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJMPDFEKSCI5TIVYG7M6KCDMGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX/action/storage_attestation","attest_author":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX/action/author_attestation","sign_citation":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX/action/citation_signature","submit_replication":"https://pith.science/pith/ZJMPDFEKSCI5TIVYG7M6KCDMGX/action/replication_record"}},"created_at":"2026-05-17T23:57:07.330615+00:00","updated_at":"2026-05-17T23:57:07.330615+00:00"}