{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PWP24PSS56CRTZGJXOCWJKYXKR","short_pith_number":"pith:PWP24PSS","canonical_record":{"source":{"id":"1706.03471","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T05:43:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a6bad5c7423263dd8978fd5a8a5d3ead40379f2f16e4cfe6c8d5135a0f608302","abstract_canon_sha256":"c0a882877eabc9309f6268d8051e3fb1b88b0d041367993cf98477c25c524b90"},"schema_version":"1.0"},"canonical_sha256":"7d9fae3e52ef8519e4c9bb8564ab175442974f828c909278e6edec54413b9d5c","source":{"kind":"arxiv","id":"1706.03471","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03471","created_at":"2026-05-18T00:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03471v2","created_at":"2026-05-18T00:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03471","created_at":"2026-05-18T00:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"PWP24PSS56CR","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PWP24PSS56CRTZGJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PWP24PSS","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PWP24PSS56CRTZGJXOCWJKYXKR","target":"record","payload":{"canonical_record":{"source":{"id":"1706.03471","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T05:43:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a6bad5c7423263dd8978fd5a8a5d3ead40379f2f16e4cfe6c8d5135a0f608302","abstract_canon_sha256":"c0a882877eabc9309f6268d8051e3fb1b88b0d041367993cf98477c25c524b90"},"schema_version":"1.0"},"canonical_sha256":"7d9fae3e52ef8519e4c9bb8564ab175442974f828c909278e6edec54413b9d5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:16.825388Z","signature_b64":"5w2UxBdoQTqRmc50jXgxEY1nvqwnydRsmAT3u02tVxLaCeyyAEFiUnMvTkvoNXgthkJkgixsLafxfcaXMjXXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d9fae3e52ef8519e4c9bb8564ab175442974f828c909278e6edec54413b9d5c","last_reissued_at":"2026-05-18T00:23:16.824849Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:16.824849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.03471","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C4vE5Gka+yiwrItZREk8VPdPK/OEB5F4DU2V1bjBfS1YuGmiHMU59ABaSpZ1IlDqLHUM+d0mTeIoi2Ky8VI4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:28:20.934033Z"},"content_sha256":"732dbebd5a76facff69b7efa054b5327cf9918d1fde8f67f13a88e73f84c7e11","schema_version":"1.0","event_id":"sha256:732dbebd5a76facff69b7efa054b5327cf9918d1fde8f67f13a88e73f84c7e11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PWP24PSS56CRTZGJXOCWJKYXKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"YellowFin and the Art of Momentum Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ML","authors_text":"Ioannis Mitliagkas, Jian Zhang","submitted_at":"2017-06-12T05:43:56Z","abstract_excerpt":"Hyperparameter tuning is one of the most time-consuming workloads in deep learning. State-of-the-art optimizers, such as AdaGrad, RMSProp and Adam, reduce this labor by adaptively tuning an individual learning rate for each variable. Recently researchers have shown renewed interest in simpler methods like momentum SGD as they may yield better test metrics. Motivated by this trend, we ask: can simple adaptive methods based on SGD perform as well or better? We revisit the momentum SGD algorithm and show that hand-tuning a single learning rate and momentum makes it competitive with Adam. We then "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03471","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sTKYBfz+AmRGDrEOYfpxXQsVEyflnRkIdf81vNu8rNsS3/ypfhBHBJBTk8llokLJuf/O1sU3ZPAVbHKF6gFnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T01:28:20.934667Z"},"content_sha256":"6618de89cff5d5aeddeda5de5a72f26db14f4452e8b06d3400b3e72a17241f9d","schema_version":"1.0","event_id":"sha256:6618de89cff5d5aeddeda5de5a72f26db14f4452e8b06d3400b3e72a17241f9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PWP24PSS56CRTZGJXOCWJKYXKR/bundle.json","state_url":"https://pith.science/pith/PWP24PSS56CRTZGJXOCWJKYXKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PWP24PSS56CRTZGJXOCWJKYXKR/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":"2026-06-08T01:28:20Z","links":{"resolver":"https://pith.science/pith/PWP24PSS56CRTZGJXOCWJKYXKR","bundle":"https://pith.science/pith/PWP24PSS56CRTZGJXOCWJKYXKR/bundle.json","state":"https://pith.science/pith/PWP24PSS56CRTZGJXOCWJKYXKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PWP24PSS56CRTZGJXOCWJKYXKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PWP24PSS56CRTZGJXOCWJKYXKR","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":"c0a882877eabc9309f6268d8051e3fb1b88b0d041367993cf98477c25c524b90","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T05:43:56Z","title_canon_sha256":"a6bad5c7423263dd8978fd5a8a5d3ead40379f2f16e4cfe6c8d5135a0f608302"},"schema_version":"1.0","source":{"id":"1706.03471","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03471","created_at":"2026-05-18T00:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03471v2","created_at":"2026-05-18T00:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03471","created_at":"2026-05-18T00:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"PWP24PSS56CR","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PWP24PSS56CRTZGJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PWP24PSS","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:6618de89cff5d5aeddeda5de5a72f26db14f4452e8b06d3400b3e72a17241f9d","target":"graph","created_at":"2026-05-18T00:23:16Z","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":"Hyperparameter tuning is one of the most time-consuming workloads in deep learning. State-of-the-art optimizers, such as AdaGrad, RMSProp and Adam, reduce this labor by adaptively tuning an individual learning rate for each variable. Recently researchers have shown renewed interest in simpler methods like momentum SGD as they may yield better test metrics. Motivated by this trend, we ask: can simple adaptive methods based on SGD perform as well or better? We revisit the momentum SGD algorithm and show that hand-tuning a single learning rate and momentum makes it competitive with Adam. We then ","authors_text":"Ioannis Mitliagkas, Jian Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T05:43:56Z","title":"YellowFin and the Art of Momentum Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03471","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":"sha256:732dbebd5a76facff69b7efa054b5327cf9918d1fde8f67f13a88e73f84c7e11","target":"record","created_at":"2026-05-18T00:23:16Z","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":"c0a882877eabc9309f6268d8051e3fb1b88b0d041367993cf98477c25c524b90","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T05:43:56Z","title_canon_sha256":"a6bad5c7423263dd8978fd5a8a5d3ead40379f2f16e4cfe6c8d5135a0f608302"},"schema_version":"1.0","source":{"id":"1706.03471","kind":"arxiv","version":2}},"canonical_sha256":"7d9fae3e52ef8519e4c9bb8564ab175442974f828c909278e6edec54413b9d5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d9fae3e52ef8519e4c9bb8564ab175442974f828c909278e6edec54413b9d5c","first_computed_at":"2026-05-18T00:23:16.824849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:16.824849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5w2UxBdoQTqRmc50jXgxEY1nvqwnydRsmAT3u02tVxLaCeyyAEFiUnMvTkvoNXgthkJkgixsLafxfcaXMjXXDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:16.825388Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.03471","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:732dbebd5a76facff69b7efa054b5327cf9918d1fde8f67f13a88e73f84c7e11","sha256:6618de89cff5d5aeddeda5de5a72f26db14f4452e8b06d3400b3e72a17241f9d"],"state_sha256":"4242a44cf6a6dd163bdee8870d155206e46dc52ef9378c2296dc1335be695077"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6vR1pYFozZLq6DuI+EjAAjn3P09+v/cO2oVDzOHxwKluKYSlb5yJEEkwnFGhlxlZR3HQrgfEvL+opwdk+MEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T01:28:20.939235Z","bundle_sha256":"d712a3ab65ade9f14ac272870ee5664db89cf397175488537537093c1d93ba5d"}}