{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HEKKFW6HNUEETJ3PKRBXLYAXYP","short_pith_number":"pith:HEKKFW6H","canonical_record":{"source":{"id":"1905.10757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T08:07:55Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4ff1a72be106732f14b48ded688edbdddec260fd27c61d3bf0c53af36076e181","abstract_canon_sha256":"98bb2a6dad1f44b5406be335aa4e49944fc9ea8e7cfec416e39d914ca74f4aa4"},"schema_version":"1.0"},"canonical_sha256":"3914a2dbc76d0849a76f544375e017c3ed9ddcc1b1b31b6a9437d9ffbe7823c4","source":{"kind":"arxiv","id":"1905.10757","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10757","created_at":"2026-05-17T23:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10757v1","created_at":"2026-05-17T23:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10757","created_at":"2026-05-17T23:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"HEKKFW6HNUEE","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HEKKFW6HNUEETJ3P","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HEKKFW6H","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HEKKFW6HNUEETJ3PKRBXLYAXYP","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T08:07:55Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4ff1a72be106732f14b48ded688edbdddec260fd27c61d3bf0c53af36076e181","abstract_canon_sha256":"98bb2a6dad1f44b5406be335aa4e49944fc9ea8e7cfec416e39d914ca74f4aa4"},"schema_version":"1.0"},"canonical_sha256":"3914a2dbc76d0849a76f544375e017c3ed9ddcc1b1b31b6a9437d9ffbe7823c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:05.359448Z","signature_b64":"XVsGkNf/LWsZd1nymxDFwDG40Lmr/+c03dk4OU1713gRRFFe20wclWSUsuPl9GCr144yPMgZv7/9xcwIH4aEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3914a2dbc76d0849a76f544375e017c3ed9ddcc1b1b31b6a9437d9ffbe7823c4","last_reissued_at":"2026-05-17T23:45:05.358886Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:05.358886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10757","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/S+ozEVs0kp1elhc3Ymi2Mf0+ax8joqrkgtM3VCu+6wmCURxEHNK4lEHem9Ujbq7AANi6UX9wXB61AoY8lYTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:16:51.493067Z"},"content_sha256":"7285fe726c5ee35f25cfef98ed8376310bae2269037d033f2ef82215ddc53f5a","schema_version":"1.0","event_id":"sha256:7285fe726c5ee35f25cfef98ed8376310bae2269037d033f2ef82215ddc53f5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HEKKFW6HNUEETJ3PKRBXLYAXYP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Gradient Methods with Block Diagonal Matrix Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelie C. Lozano, Eunho Yang, Jihun Yun","submitted_at":"2019-05-26T08:07:55Z","abstract_excerpt":"Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class of algorithms includes Adagrad, RMSprop, Adam, and recent extensions. All these algorithms have adopted diagonal matrix adaptation, due to the prohibitive computational burden of manipulating full matrices in high-dimensions. In this paper, we show that block-diagonal matrix adaptation can be a practical and powerful solution that can effectively utilize structural characteristics of deep learning architectures, and significantly imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10757","kind":"arxiv","version":1},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Irzy4d/f41E/8h791Tl1XTO6s6mfnlho904F8OKaquRhDkAgRSLN/aw5NcVtkV196eQY5G6TYon4RaPW419wCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:16:51.493461Z"},"content_sha256":"29e973ecc42e15d1950cbcbb2761eb7d404cf623bbdd97ee90ca8db3435655aa","schema_version":"1.0","event_id":"sha256:29e973ecc42e15d1950cbcbb2761eb7d404cf623bbdd97ee90ca8db3435655aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HEKKFW6HNUEETJ3PKRBXLYAXYP/bundle.json","state_url":"https://pith.science/pith/HEKKFW6HNUEETJ3PKRBXLYAXYP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HEKKFW6HNUEETJ3PKRBXLYAXYP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T06:16:51Z","links":{"resolver":"https://pith.science/pith/HEKKFW6HNUEETJ3PKRBXLYAXYP","bundle":"https://pith.science/pith/HEKKFW6HNUEETJ3PKRBXLYAXYP/bundle.json","state":"https://pith.science/pith/HEKKFW6HNUEETJ3PKRBXLYAXYP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HEKKFW6HNUEETJ3PKRBXLYAXYP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HEKKFW6HNUEETJ3PKRBXLYAXYP","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":"98bb2a6dad1f44b5406be335aa4e49944fc9ea8e7cfec416e39d914ca74f4aa4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T08:07:55Z","title_canon_sha256":"4ff1a72be106732f14b48ded688edbdddec260fd27c61d3bf0c53af36076e181"},"schema_version":"1.0","source":{"id":"1905.10757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10757","created_at":"2026-05-17T23:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10757v1","created_at":"2026-05-17T23:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10757","created_at":"2026-05-17T23:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"HEKKFW6HNUEE","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HEKKFW6HNUEETJ3P","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HEKKFW6H","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:29e973ecc42e15d1950cbcbb2761eb7d404cf623bbdd97ee90ca8db3435655aa","target":"graph","created_at":"2026-05-17T23:45:05Z","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":"Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class of algorithms includes Adagrad, RMSprop, Adam, and recent extensions. All these algorithms have adopted diagonal matrix adaptation, due to the prohibitive computational burden of manipulating full matrices in high-dimensions. In this paper, we show that block-diagonal matrix adaptation can be a practical and powerful solution that can effectively utilize structural characteristics of deep learning architectures, and significantly imp","authors_text":"Aurelie C. Lozano, Eunho Yang, Jihun Yun","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T08:07:55Z","title":"Stochastic Gradient Methods with Block Diagonal Matrix Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10757","kind":"arxiv","version":1},"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":"sha256:7285fe726c5ee35f25cfef98ed8376310bae2269037d033f2ef82215ddc53f5a","target":"record","created_at":"2026-05-17T23:45:05Z","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":"98bb2a6dad1f44b5406be335aa4e49944fc9ea8e7cfec416e39d914ca74f4aa4","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T08:07:55Z","title_canon_sha256":"4ff1a72be106732f14b48ded688edbdddec260fd27c61d3bf0c53af36076e181"},"schema_version":"1.0","source":{"id":"1905.10757","kind":"arxiv","version":1}},"canonical_sha256":"3914a2dbc76d0849a76f544375e017c3ed9ddcc1b1b31b6a9437d9ffbe7823c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3914a2dbc76d0849a76f544375e017c3ed9ddcc1b1b31b6a9437d9ffbe7823c4","first_computed_at":"2026-05-17T23:45:05.358886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:05.358886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XVsGkNf/LWsZd1nymxDFwDG40Lmr/+c03dk4OU1713gRRFFe20wclWSUsuPl9GCr144yPMgZv7/9xcwIH4aEDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:05.359448Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7285fe726c5ee35f25cfef98ed8376310bae2269037d033f2ef82215ddc53f5a","sha256:29e973ecc42e15d1950cbcbb2761eb7d404cf623bbdd97ee90ca8db3435655aa"],"state_sha256":"e44a998eb1e75777df30c3eb9b7e140fe2bef21d8c22bf73683c16ce71500db7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZK63+pAT9owdciQoYDL6FZV64C/bI2xpiGILibvUBJL5nfEtX8YsFEjn9Ok+Q2yquPTkb2hb3FGCyLkXIegxCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T06:16:51.495883Z","bundle_sha256":"74c051c54e7583d8cd9879a68f3e6d2f84fc442717a7fd2afb876172d7ab3861"}}