{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:POR5YBSLDCINLLCKCDXNA6B6KE","short_pith_number":"pith:POR5YBSL","canonical_record":{"source":{"id":"1908.00700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T04:20:34Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"36d1e794acb98046729e86302d3c4f89e091db69c723ed9346ee5a7d38f991d3","abstract_canon_sha256":"d15b8b969f0a71a2fd73eb2e0b5f89547eebbb8eb5e690dbf662a782e25280a2"},"schema_version":"1.0"},"canonical_sha256":"7ba3dc064b1890d5ac4a10eed0783e512355228b39e052765632db836196bbbf","source":{"kind":"arxiv","id":"1908.00700","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.00700","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"1908.00700v2","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.00700","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"POR5YBSLDCIN","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"POR5YBSLDCINLLCK","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"POR5YBSL","created_at":"2026-07-05T00:03:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:POR5YBSLDCINLLCKCDXNA6B6KE","target":"record","payload":{"canonical_record":{"source":{"id":"1908.00700","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T04:20:34Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"36d1e794acb98046729e86302d3c4f89e091db69c723ed9346ee5a7d38f991d3","abstract_canon_sha256":"d15b8b969f0a71a2fd73eb2e0b5f89547eebbb8eb5e690dbf662a782e25280a2"},"schema_version":"1.0"},"canonical_sha256":"7ba3dc064b1890d5ac4a10eed0783e512355228b39e052765632db836196bbbf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:58.152083Z","signature_b64":"OgQjcZFA9AiJiPbzxbJcsIOBgxC0flYw8QAznEHIjaBGLHWPC722uWRj6+m3BwoNdNRRTuw0e2xBgSti3EuCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ba3dc064b1890d5ac4a10eed0783e512355228b39e052765632db836196bbbf","last_reissued_at":"2026-07-05T00:03:58.151673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:58.151673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.00700","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":"2026-07-05T00:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5kKdGxMgOUryoTxTEP96Wz4jqO6q/JwzeoH9Ya/ZujV/vBQCoV7sICvD5dNIbfgRHbT4ARTmMZ0X8/zCM0ZNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:39:09.715444Z"},"content_sha256":"e868d29e07890144a21bc31c438f4cfc5b2186658ee3d12e889963f0e4c5d486","schema_version":"1.0","event_id":"sha256:e868d29e07890144a21bc31c438f4cfc5b2186658ee3d12e889963f0e4c5d486"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:POR5YBSLDCINLLCKCDXNA6B6KE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calibrating the Adaptive Learning Rate to Improve Convergence of ADAM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guannan Liang, Jinbo Bi, Qianqian Tong","submitted_at":"2019-08-02T04:20:34Z","abstract_excerpt":"Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of the problem over epochs (i.e., anisotropic scale), which may lead to issues in convergence and generalization. All existing modified AGMs actually represent efforts in revising the A-LR. Theoretically, we provide a new way to analyze the convergence of AGMs and prove that the convergence rate of \\textsc{Adam} also depends on its hyper-parameter $\\epsilon$, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.00700","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.00700/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":"2026-07-05T00:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLWLNxruxbMVKPtjOmtlPIYEqogesn6HwA6/DUls1bN8bvc2w6HoumG6jOAyETZ8zBe0cokWEKJNrK7opm/ZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T07:39:09.715969Z"},"content_sha256":"12ba9a1cc3877c3f1c3e914ca4e6a144c04840e8a507343685cd142b483d5eec","schema_version":"1.0","event_id":"sha256:12ba9a1cc3877c3f1c3e914ca4e6a144c04840e8a507343685cd142b483d5eec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POR5YBSLDCINLLCKCDXNA6B6KE/bundle.json","state_url":"https://pith.science/pith/POR5YBSLDCINLLCKCDXNA6B6KE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POR5YBSLDCINLLCKCDXNA6B6KE/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":"2026-08-16T07:39:09Z","links":{"resolver":"https://pith.science/pith/POR5YBSLDCINLLCKCDXNA6B6KE","bundle":"https://pith.science/pith/POR5YBSLDCINLLCKCDXNA6B6KE/bundle.json","state":"https://pith.science/pith/POR5YBSLDCINLLCKCDXNA6B6KE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POR5YBSLDCINLLCKCDXNA6B6KE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:POR5YBSLDCINLLCKCDXNA6B6KE","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":"d15b8b969f0a71a2fd73eb2e0b5f89547eebbb8eb5e690dbf662a782e25280a2","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T04:20:34Z","title_canon_sha256":"36d1e794acb98046729e86302d3c4f89e091db69c723ed9346ee5a7d38f991d3"},"schema_version":"1.0","source":{"id":"1908.00700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.00700","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"1908.00700v2","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.00700","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"POR5YBSLDCIN","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"POR5YBSLDCINLLCK","created_at":"2026-07-05T00:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"POR5YBSL","created_at":"2026-07-05T00:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:12ba9a1cc3877c3f1c3e914ca4e6a144c04840e8a507343685cd142b483d5eec","target":"graph","created_at":"2026-07-05T00:03:58Z","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/1908.00700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of the problem over epochs (i.e., anisotropic scale), which may lead to issues in convergence and generalization. All existing modified AGMs actually represent efforts in revising the A-LR. Theoretically, we provide a new way to analyze the convergence of AGMs and prove that the convergence rate of \\textsc{Adam} also depends on its hyper-parameter $\\epsilon$, w","authors_text":"Guannan Liang, Jinbo Bi, Qianqian Tong","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T04:20:34Z","title":"Calibrating the Adaptive Learning Rate to Improve Convergence of ADAM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.00700","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:e868d29e07890144a21bc31c438f4cfc5b2186658ee3d12e889963f0e4c5d486","target":"record","created_at":"2026-07-05T00:03:58Z","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":"d15b8b969f0a71a2fd73eb2e0b5f89547eebbb8eb5e690dbf662a782e25280a2","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-02T04:20:34Z","title_canon_sha256":"36d1e794acb98046729e86302d3c4f89e091db69c723ed9346ee5a7d38f991d3"},"schema_version":"1.0","source":{"id":"1908.00700","kind":"arxiv","version":2}},"canonical_sha256":"7ba3dc064b1890d5ac4a10eed0783e512355228b39e052765632db836196bbbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ba3dc064b1890d5ac4a10eed0783e512355228b39e052765632db836196bbbf","first_computed_at":"2026-07-05T00:03:58.151673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:03:58.151673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OgQjcZFA9AiJiPbzxbJcsIOBgxC0flYw8QAznEHIjaBGLHWPC722uWRj6+m3BwoNdNRRTuw0e2xBgSti3EuCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:03:58.152083Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.00700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e868d29e07890144a21bc31c438f4cfc5b2186658ee3d12e889963f0e4c5d486","sha256:12ba9a1cc3877c3f1c3e914ca4e6a144c04840e8a507343685cd142b483d5eec"],"state_sha256":"756ac8539cfd4f6b07e3b2e52e126abd6c234d91fd664f8d26fe3e49a35874fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2kUP2UzppzGTrI2YaFkCVzku1FAzWrrBg7+/g7GTljawyd3UQCZKy4ObLx+FfaOgxP+dO1vu56l6EETtAZ07Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T07:39:09.721692Z","bundle_sha256":"97ea8da4fd27601bff9e6ecc7d5e7540f866b9ede718ca0de9c9422ca35fa4ce"}}