{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MQHO5YEFCJNICSRGMBEL3YUE5H","short_pith_number":"pith:MQHO5YEF","schema_version":"1.0","canonical_sha256":"640eeee085125a814a266048bde284e9e1c1a28521d2a401ce097f8d63404017","source":{"kind":"arxiv","id":"1609.03319","version":2},"attestation_state":"computed","paper":{"title":"CompAdaGrad: A Compressed, Complementary, Computationally-Efficient Adaptive Gradient Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alistair Rendell, Anish Varghese, Christfried Webers, Nishant A. Mehta","submitted_at":"2016-09-12T09:06:44Z","abstract_excerpt":"The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. The method's full-matrix incarnation offers much better theoretical guarantees and potentially better empirical performance than its diagonal version; however, this version is computationally prohibitive and so the simpler diagonal version often is used in practice. We introduce a new method, CompAdaGrad, that navigates the space between these two schemes and show that this meth"},"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":"1609.03319","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-12T09:06:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b5ceaf3fe86ccc06b1ea6ba87c5c796e36b4939acd797926e8d985828c5d89b7","abstract_canon_sha256":"14e50b3dd2928d67b27d09ebb82327bc2f3391e6d080957434f272d5702da991"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:17.223491Z","signature_b64":"GnJb3pajhKeEc+0Rs27O8Pr5HJKQEZKDTn8SL5iyfpBTjq7Pr/FH2nqTAUKTO+tdi9UjhgMSHnVnEzCqQAC3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"640eeee085125a814a266048bde284e9e1c1a28521d2a401ce097f8d63404017","last_reissued_at":"2026-05-18T01:03:17.223057Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:17.223057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompAdaGrad: A Compressed, Complementary, Computationally-Efficient Adaptive Gradient Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alistair Rendell, Anish Varghese, Christfried Webers, Nishant A. Mehta","submitted_at":"2016-09-12T09:06:44Z","abstract_excerpt":"The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. The method's full-matrix incarnation offers much better theoretical guarantees and potentially better empirical performance than its diagonal version; however, this version is computationally prohibitive and so the simpler diagonal version often is used in practice. We introduce a new method, CompAdaGrad, that navigates the space between these two schemes and show that this meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03319","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":"1609.03319","created_at":"2026-05-18T01:03:17.223118+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.03319v2","created_at":"2026-05-18T01:03:17.223118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03319","created_at":"2026-05-18T01:03:17.223118+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQHO5YEFCJNI","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQHO5YEFCJNICSRG","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQHO5YEF","created_at":"2026-05-18T12:30:32.724797+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/MQHO5YEFCJNICSRGMBEL3YUE5H","json":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H.json","graph_json":"https://pith.science/api/pith-number/MQHO5YEFCJNICSRGMBEL3YUE5H/graph.json","events_json":"https://pith.science/api/pith-number/MQHO5YEFCJNICSRGMBEL3YUE5H/events.json","paper":"https://pith.science/paper/MQHO5YEF"},"agent_actions":{"view_html":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H","download_json":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H.json","view_paper":"https://pith.science/paper/MQHO5YEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.03319&json=true","fetch_graph":"https://pith.science/api/pith-number/MQHO5YEFCJNICSRGMBEL3YUE5H/graph.json","fetch_events":"https://pith.science/api/pith-number/MQHO5YEFCJNICSRGMBEL3YUE5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H/action/storage_attestation","attest_author":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H/action/author_attestation","sign_citation":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H/action/citation_signature","submit_replication":"https://pith.science/pith/MQHO5YEFCJNICSRGMBEL3YUE5H/action/replication_record"}},"created_at":"2026-05-18T01:03:17.223118+00:00","updated_at":"2026-05-18T01:03:17.223118+00:00"}