{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NV3XF3AOP5TI2F7AGLATOMPRI4","short_pith_number":"pith:NV3XF3AO","schema_version":"1.0","canonical_sha256":"6d7772ec0e7f668d17e032c13731f1472f176bd69b51ca07b486f1b9ef897f74","source":{"kind":"arxiv","id":"2210.08371","version":2},"attestation_state":"computed","paper":{"title":"Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Lichen Zhang, Yitan Wang, Zhao Song, Zheng Yu","submitted_at":"2022-10-15T20:44:15Z","abstract_excerpt":"Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching scheme for the first order method in large-scale distributed learning setting, such that the communication costs between distributed agents are saved while the convergence of the algorithms is still guaranteed. Given gradient information in a high dimension $d$, the agent passes the compressed information processed by a sketching matrix $R\\in \\mathbb{R}^{s\\times"},"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":"2210.08371","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T20:44:15Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"7cf3bf4f6cf0f4be25dbc1cc3d508e17f0211c29a1840b07b21d3f5b15ff6c58","abstract_canon_sha256":"42602fb28114bb0ad1feb6047a216ae3885a148c9c3576d7c9d79cb7c01abe83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:18.148331Z","signature_b64":"z7wcCL9CgyPvqTS1/TnuCOOyavV5+LySiHcbCPagpg212rV9N7sTcsCoPCaQWQrrsYiKzwx8mI+NWjvDDPHSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d7772ec0e7f668d17e032c13731f1472f176bd69b51ca07b486f1b9ef897f74","last_reissued_at":"2026-07-05T06:18:18.147880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:18.147880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Lichen Zhang, Yitan Wang, Zhao Song, Zheng Yu","submitted_at":"2022-10-15T20:44:15Z","abstract_excerpt":"Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching scheme for the first order method in large-scale distributed learning setting, such that the communication costs between distributed agents are saved while the convergence of the algorithms is still guaranteed. Given gradient information in a high dimension $d$, the agent passes the compressed information processed by a sketching matrix $R\\in \\mathbb{R}^{s\\times"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08371","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.08371/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2210.08371","created_at":"2026-07-05T06:18:18.147951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08371v2","created_at":"2026-07-05T06:18:18.147951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08371","created_at":"2026-07-05T06:18:18.147951+00:00"},{"alias_kind":"pith_short_12","alias_value":"NV3XF3AOP5TI","created_at":"2026-07-05T06:18:18.147951+00:00"},{"alias_kind":"pith_short_16","alias_value":"NV3XF3AOP5TI2F7A","created_at":"2026-07-05T06:18:18.147951+00:00"},{"alias_kind":"pith_short_8","alias_value":"NV3XF3AO","created_at":"2026-07-05T06:18:18.147951+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/NV3XF3AOP5TI2F7AGLATOMPRI4","json":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4.json","graph_json":"https://pith.science/api/pith-number/NV3XF3AOP5TI2F7AGLATOMPRI4/graph.json","events_json":"https://pith.science/api/pith-number/NV3XF3AOP5TI2F7AGLATOMPRI4/events.json","paper":"https://pith.science/paper/NV3XF3AO"},"agent_actions":{"view_html":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4","download_json":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4.json","view_paper":"https://pith.science/paper/NV3XF3AO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08371&json=true","fetch_graph":"https://pith.science/api/pith-number/NV3XF3AOP5TI2F7AGLATOMPRI4/graph.json","fetch_events":"https://pith.science/api/pith-number/NV3XF3AOP5TI2F7AGLATOMPRI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4/action/storage_attestation","attest_author":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4/action/author_attestation","sign_citation":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4/action/citation_signature","submit_replication":"https://pith.science/pith/NV3XF3AOP5TI2F7AGLATOMPRI4/action/replication_record"}},"created_at":"2026-07-05T06:18:18.147951+00:00","updated_at":"2026-07-05T06:18:18.147951+00:00"}