{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:CJYKRI5RYZRE6IC7DCXLCBB6ZT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"51e052a579b5ce3a67afa9210d0c57398b9754ee13122b3075eadb8f176c23ea","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:43:08Z","title_canon_sha256":"dceb43ed3b22d8fd4aece6a04dfa52431df6896d4a4c4f80f0d1765ac9dd0db8"},"schema_version":"1.0","source":{"id":"1902.00179","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00179","created_at":"2026-05-17T23:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00179v2","created_at":"2026-05-17T23:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00179","created_at":"2026-05-17T23:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"CJYKRI5RYZRE","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"CJYKRI5RYZRE6IC7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"CJYKRI5R","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:8ac7f828e9d6e09bf9fb81aa07b4db54a998a1fd5793b93b7556992526e3aa4a","target":"graph","created_at":"2026-05-17T23:52:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Many popular first-order optimization methods (e.g., Momentum, AdaGrad, Adam) accelerate the convergence rate of deep learning models. However, these algorithms require auxiliary parameters, which cost additional memory proportional to the number of parameters in the model. The problem is becoming more severe as deep learning models continue to grow larger in order to learn from complex, large-scale datasets. Our proposed solution is to maintain a linear sketch to compress the auxiliary variables. We demonstrate that our technique has the same performance as the full-sized baseline, while usin","authors_text":"Anastasios Kyrillidis, Anshumali Shrivastava, Ryan Spring, Vijai Mohan","cross_cats":["cs.DS","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:43:08Z","title":"Compressing Gradient Optimizers via Count-Sketches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00179","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:89267e7a843f8994081c2dcde5af93a14c8f2c2ebf0a5421051091b4c5df9b53","target":"record","created_at":"2026-05-17T23:52:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"51e052a579b5ce3a67afa9210d0c57398b9754ee13122b3075eadb8f176c23ea","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T04:43:08Z","title_canon_sha256":"dceb43ed3b22d8fd4aece6a04dfa52431df6896d4a4c4f80f0d1765ac9dd0db8"},"schema_version":"1.0","source":{"id":"1902.00179","kind":"arxiv","version":2}},"canonical_sha256":"1270a8a3b1c6624f205f18aeb1043eccfbeb207a8702ff2858c52b4d1a30734a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1270a8a3b1c6624f205f18aeb1043eccfbeb207a8702ff2858c52b4d1a30734a","first_computed_at":"2026-05-17T23:52:38.008294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:38.008294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kUvnynhSflLXhJml3BwxVLUJbNIoVHK9sn0njSMAPCXd+lztMHXQTl+zDHnm/g5gEEwwuCXVCNdWC21dt+YYDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:38.009024Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00179","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89267e7a843f8994081c2dcde5af93a14c8f2c2ebf0a5421051091b4c5df9b53","sha256:8ac7f828e9d6e09bf9fb81aa07b4db54a998a1fd5793b93b7556992526e3aa4a"],"state_sha256":"ecbeb73958447b0f871ea49557d6be591c7f6f1d56549510735fffbf48a692c3"}