{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AIO2C3GAMEPOKWSG4O6FJH4LZA","short_pith_number":"pith:AIO2C3GA","canonical_record":{"source":{"id":"1902.07399","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T04:31:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a08e875ed65b376f4526820575719aa30334085d65409be93c061c7d7fbbd438","abstract_canon_sha256":"9008c245e19bd236f6282e6886c6cb60e5a626f44fa44d52944bb1e5e45dc6fb"},"schema_version":"1.0"},"canonical_sha256":"021da16cc0611ee55a46e3bc549f8bc80b918feaec76e3199619c64925a2e8c2","source":{"kind":"arxiv","id":"1902.07399","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07399","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07399v4","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07399","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"AIO2C3GAMEPO","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"pith_short_16","alias_value":"AIO2C3GAMEPOKWSG","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"pith_short_8","alias_value":"AIO2C3GA","created_at":"2026-07-05T01:23:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AIO2C3GAMEPOKWSG4O6FJH4LZA","target":"record","payload":{"canonical_record":{"source":{"id":"1902.07399","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T04:31:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a08e875ed65b376f4526820575719aa30334085d65409be93c061c7d7fbbd438","abstract_canon_sha256":"9008c245e19bd236f6282e6886c6cb60e5a626f44fa44d52944bb1e5e45dc6fb"},"schema_version":"1.0"},"canonical_sha256":"021da16cc0611ee55a46e3bc549f8bc80b918feaec76e3199619c64925a2e8c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:53.519994Z","signature_b64":"kGLebwqqD4HHAWUX+xnPF45u7fBul+qREKTLmzzohYaMeDfL8+WYvnPfCEOlYutCWFrORSZQBIA2TmnqEOkJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"021da16cc0611ee55a46e3bc549f8bc80b918feaec76e3199619c64925a2e8c2","last_reissued_at":"2026-07-05T01:23:53.519531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:53.519531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.07399","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MbmHnaH22SaTQH5yxeMaG9PhH8iapX7aIZa3GrRp2eJ0T0PMxh7/ITdYMFWKCRqMRIPoo6P29eIsiPAaG2FOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T14:54:20.796903Z"},"content_sha256":"18b2b3b987f4333d53c06c6c1fc39d17411eea5bee1507e29c43ec5feb3b1bc1","schema_version":"1.0","event_id":"sha256:18b2b3b987f4333d53c06c6c1fc39d17411eea5bee1507e29c43ec5feb3b1bc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AIO2C3GAMEPOKWSG4O6FJH4LZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Rahul Yedida, Snehanshu Saha, Tejas Prashanth","submitted_at":"2019-02-20T04:31:11Z","abstract_excerpt":"Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout rate. Arguably, the learning rate is the most important of these to tune, and this has gained more attention in recent works. In this paper, we propose a novel method to compute the learning rate for training deep neural networks with stochastic gradient descent. We first derive a theoretical framework to compute learning rates dynamically based on the Lipschitz constant of the loss function. We then extend this fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07399","kind":"arxiv","version":4},"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/1902.07399/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iw5YulVnNZ4IbGboBkwX91LZpoSptOpqmwjZKeXSVaub+QKxZdq/cx5cV1rOcr9fuetzRexH1380GC4Iwsj7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T14:54:20.797268Z"},"content_sha256":"bd89398ac8f7f46392608c01dbd98cae23936e0f9e6740ddbf7295bf1ada43b2","schema_version":"1.0","event_id":"sha256:bd89398ac8f7f46392608c01dbd98cae23936e0f9e6740ddbf7295bf1ada43b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AIO2C3GAMEPOKWSG4O6FJH4LZA/bundle.json","state_url":"https://pith.science/pith/AIO2C3GAMEPOKWSG4O6FJH4LZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AIO2C3GAMEPOKWSG4O6FJH4LZA/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":"2026-07-13T14:54:20Z","links":{"resolver":"https://pith.science/pith/AIO2C3GAMEPOKWSG4O6FJH4LZA","bundle":"https://pith.science/pith/AIO2C3GAMEPOKWSG4O6FJH4LZA/bundle.json","state":"https://pith.science/pith/AIO2C3GAMEPOKWSG4O6FJH4LZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AIO2C3GAMEPOKWSG4O6FJH4LZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AIO2C3GAMEPOKWSG4O6FJH4LZA","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":"9008c245e19bd236f6282e6886c6cb60e5a626f44fa44d52944bb1e5e45dc6fb","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T04:31:11Z","title_canon_sha256":"a08e875ed65b376f4526820575719aa30334085d65409be93c061c7d7fbbd438"},"schema_version":"1.0","source":{"id":"1902.07399","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07399","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07399v4","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07399","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"AIO2C3GAMEPO","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"pith_short_16","alias_value":"AIO2C3GAMEPOKWSG","created_at":"2026-07-05T01:23:53Z"},{"alias_kind":"pith_short_8","alias_value":"AIO2C3GA","created_at":"2026-07-05T01:23:53Z"}],"graph_snapshots":[{"event_id":"sha256:bd89398ac8f7f46392608c01dbd98cae23936e0f9e6740ddbf7295bf1ada43b2","target":"graph","created_at":"2026-07-05T01:23:53Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1902.07399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout rate. Arguably, the learning rate is the most important of these to tune, and this has gained more attention in recent works. In this paper, we propose a novel method to compute the learning rate for training deep neural networks with stochastic gradient descent. We first derive a theoretical framework to compute learning rates dynamically based on the Lipschitz constant of the loss function. We then extend this fra","authors_text":"Rahul Yedida, Snehanshu Saha, Tejas Prashanth","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T04:31:11Z","title":"LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07399","kind":"arxiv","version":4},"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":"sha256:18b2b3b987f4333d53c06c6c1fc39d17411eea5bee1507e29c43ec5feb3b1bc1","target":"record","created_at":"2026-07-05T01:23:53Z","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":"9008c245e19bd236f6282e6886c6cb60e5a626f44fa44d52944bb1e5e45dc6fb","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-02-20T04:31:11Z","title_canon_sha256":"a08e875ed65b376f4526820575719aa30334085d65409be93c061c7d7fbbd438"},"schema_version":"1.0","source":{"id":"1902.07399","kind":"arxiv","version":4}},"canonical_sha256":"021da16cc0611ee55a46e3bc549f8bc80b918feaec76e3199619c64925a2e8c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"021da16cc0611ee55a46e3bc549f8bc80b918feaec76e3199619c64925a2e8c2","first_computed_at":"2026-07-05T01:23:53.519531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:53.519531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kGLebwqqD4HHAWUX+xnPF45u7fBul+qREKTLmzzohYaMeDfL8+WYvnPfCEOlYutCWFrORSZQBIA2TmnqEOkJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:53.519994Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.07399","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18b2b3b987f4333d53c06c6c1fc39d17411eea5bee1507e29c43ec5feb3b1bc1","sha256:bd89398ac8f7f46392608c01dbd98cae23936e0f9e6740ddbf7295bf1ada43b2"],"state_sha256":"840b0c3395510a79ffdec647b5469425ec190ad2b334be9cd10d467097ba15a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uep+VKXdIbyopGXy7kpsErd14VPMOQLLNBo0Jv7STIsVS9ISkqJTlJSQbC2b4kZMUSHzDKNqAqFzHt7I76ocBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T14:54:20.799275Z","bundle_sha256":"8b8edf4de097eaddd6ccdccf42b09f758078a79bc9049db354bfd4c2423526ea"}}