{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OOE3GK5GIR4YSWQ7FKPZKYFBPK","short_pith_number":"pith:OOE3GK5G","canonical_record":{"source":{"id":"1805.09386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T19:08:19Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4b68ca232a7af2c5c8c8fdedf66600a2503807b5c9c107ee0e2bed0bfd21943f","abstract_canon_sha256":"56127eda50924a132cc07e840f5a6abb40a8299e7a267d40bcb4cb6130270286"},"schema_version":"1.0"},"canonical_sha256":"7389b32ba64479895a1f2a9f9560a17aa204b4a43fdb0c9263262d4b08dc2071","source":{"kind":"arxiv","id":"1805.09386","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09386","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09386v1","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09386","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"OOE3GK5GIR4Y","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OOE3GK5GIR4YSWQ7","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OOE3GK5G","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OOE3GK5GIR4YSWQ7FKPZKYFBPK","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T19:08:19Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"4b68ca232a7af2c5c8c8fdedf66600a2503807b5c9c107ee0e2bed0bfd21943f","abstract_canon_sha256":"56127eda50924a132cc07e840f5a6abb40a8299e7a267d40bcb4cb6130270286"},"schema_version":"1.0"},"canonical_sha256":"7389b32ba64479895a1f2a9f9560a17aa204b4a43fdb0c9263262d4b08dc2071","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:04.209799Z","signature_b64":"pMtZbT6rcjgeqS8/aIHBI8lwiGNc2XD006dA/5xRQ1r79ORlVswpW7atto6JW/HhByCjqYPLOYg19D9UTfLMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7389b32ba64479895a1f2a9f9560a17aa204b4a43fdb0c9263262d4b08dc2071","last_reissued_at":"2026-05-18T00:15:04.209050Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:04.209050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09386","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":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4SQuYHHdb2cbhHuD+P+KZYGQ1GG00jUrZlmHt5j6E8f7mmcuZVBITK2bkLFddsNHyN21ry2G0Pf3xup2YL1DDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:31:34.949811Z"},"content_sha256":"a2533f7351406a18038c8d818abfda47e2ae8aef1e98f88a87f5a531ea228fae","schema_version":"1.0","event_id":"sha256:a2533f7351406a18038c8d818abfda47e2ae8aef1e98f88a87f5a531ea228fae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OOE3GK5GIR4YSWQ7FKPZKYFBPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictive Local Smoothness for Stochastic Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bineng Zhong, Hongfu Liu, Jun Li, Yue Wu, Yun Fu","submitted_at":"2018-05-23T19:08:19Z","abstract_excerpt":"Stochastic gradient methods are dominant in nonconvex optimization especially for deep models but have low asymptotical convergence due to the fixed smoothness. To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS). First, we create a convergence condition to build a learning rate which varies adaptively with local smoothness. Second, the local smoothness can be predicted by the latest gradients. Third, we use the adaptive learning rate to update the stochastic gradients for exploring linear convergen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09386","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":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9ZgdkqpYv9fPRQHTvkwZHDUuJnLqZoHRtkHgmWv0pu3Xco9Ofh5qdfF2PdA9T6WHnRoqnKEi9aeHl4Hdk04Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:31:34.950514Z"},"content_sha256":"9d1d67f99652b350819d09727d9073e2fe7a4be4ce022f01e8922f0138f0550d","schema_version":"1.0","event_id":"sha256:9d1d67f99652b350819d09727d9073e2fe7a4be4ce022f01e8922f0138f0550d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOE3GK5GIR4YSWQ7FKPZKYFBPK/bundle.json","state_url":"https://pith.science/pith/OOE3GK5GIR4YSWQ7FKPZKYFBPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOE3GK5GIR4YSWQ7FKPZKYFBPK/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":"2026-05-27T18:31:34Z","links":{"resolver":"https://pith.science/pith/OOE3GK5GIR4YSWQ7FKPZKYFBPK","bundle":"https://pith.science/pith/OOE3GK5GIR4YSWQ7FKPZKYFBPK/bundle.json","state":"https://pith.science/pith/OOE3GK5GIR4YSWQ7FKPZKYFBPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOE3GK5GIR4YSWQ7FKPZKYFBPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OOE3GK5GIR4YSWQ7FKPZKYFBPK","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":"56127eda50924a132cc07e840f5a6abb40a8299e7a267d40bcb4cb6130270286","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T19:08:19Z","title_canon_sha256":"4b68ca232a7af2c5c8c8fdedf66600a2503807b5c9c107ee0e2bed0bfd21943f"},"schema_version":"1.0","source":{"id":"1805.09386","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09386","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09386v1","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09386","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"OOE3GK5GIR4Y","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OOE3GK5GIR4YSWQ7","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OOE3GK5G","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:9d1d67f99652b350819d09727d9073e2fe7a4be4ce022f01e8922f0138f0550d","target":"graph","created_at":"2026-05-18T00:15:04Z","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":"Stochastic gradient methods are dominant in nonconvex optimization especially for deep models but have low asymptotical convergence due to the fixed smoothness. To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS). First, we create a convergence condition to build a learning rate which varies adaptively with local smoothness. Second, the local smoothness can be predicted by the latest gradients. Third, we use the adaptive learning rate to update the stochastic gradients for exploring linear convergen","authors_text":"Bineng Zhong, Hongfu Liu, Jun Li, Yue Wu, Yun Fu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T19:08:19Z","title":"Predictive Local Smoothness for Stochastic Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09386","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:a2533f7351406a18038c8d818abfda47e2ae8aef1e98f88a87f5a531ea228fae","target":"record","created_at":"2026-05-18T00:15:04Z","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":"56127eda50924a132cc07e840f5a6abb40a8299e7a267d40bcb4cb6130270286","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T19:08:19Z","title_canon_sha256":"4b68ca232a7af2c5c8c8fdedf66600a2503807b5c9c107ee0e2bed0bfd21943f"},"schema_version":"1.0","source":{"id":"1805.09386","kind":"arxiv","version":1}},"canonical_sha256":"7389b32ba64479895a1f2a9f9560a17aa204b4a43fdb0c9263262d4b08dc2071","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7389b32ba64479895a1f2a9f9560a17aa204b4a43fdb0c9263262d4b08dc2071","first_computed_at":"2026-05-18T00:15:04.209050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:04.209050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pMtZbT6rcjgeqS8/aIHBI8lwiGNc2XD006dA/5xRQ1r79ORlVswpW7atto6JW/HhByCjqYPLOYg19D9UTfLMDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:04.209799Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09386","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2533f7351406a18038c8d818abfda47e2ae8aef1e98f88a87f5a531ea228fae","sha256:9d1d67f99652b350819d09727d9073e2fe7a4be4ce022f01e8922f0138f0550d"],"state_sha256":"a20540e16c19133d4b4ecfc01965aa5674920d9deeee378591446371f4c8bfb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDXyJaCrMEa/ivQ+8amhDsykqw/ivPzFYpgcICpU88xun4snycZqkYyYOJRmy7/Y+fnjSr0PL1z+BZ2+kUMYAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T18:31:34.953668Z","bundle_sha256":"b4b2e59fb284afaf4e1a40aee54777641fd6d3ed58cd5b3aeba5474fa52857b8"}}