{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LDPGXJUHO3PLOAOC24M27EYXAR","short_pith_number":"pith:LDPGXJUH","canonical_record":{"source":{"id":"1805.06753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-05-17T13:29:33Z","cross_cats_sorted":["cs.AI","cs.LG","math.OC"],"title_canon_sha256":"1f714d42ef6c674c4992629d70971577007c64436c548adcd238045d7ef8d4c2","abstract_canon_sha256":"0d3a9b7751147d10d737db1888c955b3d678410a09c54baae064ee9300d4734f"},"schema_version":"1.0"},"canonical_sha256":"58de6ba68776deb701c2d719af9317046b4ab50ace282984ddd7e3aa9dbbd8c5","source":{"kind":"arxiv","id":"1805.06753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06753","created_at":"2026-05-18T00:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06753v1","created_at":"2026-05-18T00:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06753","created_at":"2026-05-18T00:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"LDPGXJUHO3PL","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LDPGXJUHO3PLOAOC","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LDPGXJUH","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LDPGXJUHO3PLOAOC24M27EYXAR","target":"record","payload":{"canonical_record":{"source":{"id":"1805.06753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-05-17T13:29:33Z","cross_cats_sorted":["cs.AI","cs.LG","math.OC"],"title_canon_sha256":"1f714d42ef6c674c4992629d70971577007c64436c548adcd238045d7ef8d4c2","abstract_canon_sha256":"0d3a9b7751147d10d737db1888c955b3d678410a09c54baae064ee9300d4734f"},"schema_version":"1.0"},"canonical_sha256":"58de6ba68776deb701c2d719af9317046b4ab50ace282984ddd7e3aa9dbbd8c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:43.448573Z","signature_b64":"ORBnY9UFbTBz18oeW+vcxQxaFEN6jQvzUouHDyTopwC1tlDSCAukojvwNvMFWX+Rfznu6V09EUUCBJXXqdIVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58de6ba68776deb701c2d719af9317046b4ab50ace282984ddd7e3aa9dbbd8c5","last_reissued_at":"2026-05-18T00:15:43.448048Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:43.448048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.06753","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":"2026-05-18T00:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RjRs0/Lh0dcxhPPzdjOHdTr/NM/x3kjZnpzcBKMh20xEzAJZIaGlQM50C7uPtk2Sfw19CVAUKk8i7vcw///QAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T04:16:44.820766Z"},"content_sha256":"4438b56c21d13a2004778517025f004a8d38ff6dad0c32011e622c990c534d5c","schema_version":"1.0","event_id":"sha256:4438b56c21d13a2004778517025f004a8d38ff6dad0c32011e622c990c534d5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LDPGXJUHO3PLOAOC24M27EYXAR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpolatron: Interpolation or Extrapolation Schemes to Accelerate Optimization for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Guangzeng Xie, Shuchang Zhou, Yitan Wang, Zhihua Zhang","submitted_at":"2018-05-17T13:29:33Z","abstract_excerpt":"In this paper we explore acceleration techniques for large scale nonconvex optimization problems with special focuses on deep neural networks. The extrapolation scheme is a classical approach for accelerating stochastic gradient descent for convex optimization, but it does not work well for nonconvex optimization typically. Alternatively, we propose an interpolation scheme to accelerate nonconvex optimization and call the method Interpolatron. We explain motivation behind Interpolatron and conduct a thorough empirical analysis. Empirical results on DNNs of great depths (e.g., 98-layer ResNet a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06753","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":"2026-05-18T00:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gs7v33A8dRD7YbI7Zj9evjsFoO7ILl5xupKlWy/cMCKFVAPpHxg25bjY3zIoJTW8rKTMuMK7eNRdu31hg7gIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T04:16:44.821460Z"},"content_sha256":"1827fc0f4716b424862a01f1ef960d37002c2fbc917c90dce68134066d274612","schema_version":"1.0","event_id":"sha256:1827fc0f4716b424862a01f1ef960d37002c2fbc917c90dce68134066d274612"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LDPGXJUHO3PLOAOC24M27EYXAR/bundle.json","state_url":"https://pith.science/pith/LDPGXJUHO3PLOAOC24M27EYXAR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LDPGXJUHO3PLOAOC24M27EYXAR/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":"2026-06-11T04:16:44Z","links":{"resolver":"https://pith.science/pith/LDPGXJUHO3PLOAOC24M27EYXAR","bundle":"https://pith.science/pith/LDPGXJUHO3PLOAOC24M27EYXAR/bundle.json","state":"https://pith.science/pith/LDPGXJUHO3PLOAOC24M27EYXAR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LDPGXJUHO3PLOAOC24M27EYXAR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LDPGXJUHO3PLOAOC24M27EYXAR","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":"0d3a9b7751147d10d737db1888c955b3d678410a09c54baae064ee9300d4734f","cross_cats_sorted":["cs.AI","cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-05-17T13:29:33Z","title_canon_sha256":"1f714d42ef6c674c4992629d70971577007c64436c548adcd238045d7ef8d4c2"},"schema_version":"1.0","source":{"id":"1805.06753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.06753","created_at":"2026-05-18T00:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"1805.06753v1","created_at":"2026-05-18T00:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.06753","created_at":"2026-05-18T00:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"LDPGXJUHO3PL","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LDPGXJUHO3PLOAOC","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LDPGXJUH","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:1827fc0f4716b424862a01f1ef960d37002c2fbc917c90dce68134066d274612","target":"graph","created_at":"2026-05-18T00:15:43Z","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":"In this paper we explore acceleration techniques for large scale nonconvex optimization problems with special focuses on deep neural networks. The extrapolation scheme is a classical approach for accelerating stochastic gradient descent for convex optimization, but it does not work well for nonconvex optimization typically. Alternatively, we propose an interpolation scheme to accelerate nonconvex optimization and call the method Interpolatron. We explain motivation behind Interpolatron and conduct a thorough empirical analysis. Empirical results on DNNs of great depths (e.g., 98-layer ResNet a","authors_text":"Guangzeng Xie, Shuchang Zhou, Yitan Wang, Zhihua Zhang","cross_cats":["cs.AI","cs.LG","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-05-17T13:29:33Z","title":"Interpolatron: Interpolation or Extrapolation Schemes to Accelerate Optimization for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.06753","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":"sha256:4438b56c21d13a2004778517025f004a8d38ff6dad0c32011e622c990c534d5c","target":"record","created_at":"2026-05-18T00:15:43Z","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":"0d3a9b7751147d10d737db1888c955b3d678410a09c54baae064ee9300d4734f","cross_cats_sorted":["cs.AI","cs.LG","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2018-05-17T13:29:33Z","title_canon_sha256":"1f714d42ef6c674c4992629d70971577007c64436c548adcd238045d7ef8d4c2"},"schema_version":"1.0","source":{"id":"1805.06753","kind":"arxiv","version":1}},"canonical_sha256":"58de6ba68776deb701c2d719af9317046b4ab50ace282984ddd7e3aa9dbbd8c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58de6ba68776deb701c2d719af9317046b4ab50ace282984ddd7e3aa9dbbd8c5","first_computed_at":"2026-05-18T00:15:43.448048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:43.448048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ORBnY9UFbTBz18oeW+vcxQxaFEN6jQvzUouHDyTopwC1tlDSCAukojvwNvMFWX+Rfznu6V09EUUCBJXXqdIVCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:43.448573Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.06753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4438b56c21d13a2004778517025f004a8d38ff6dad0c32011e622c990c534d5c","sha256:1827fc0f4716b424862a01f1ef960d37002c2fbc917c90dce68134066d274612"],"state_sha256":"f8df8e5091599d8786f25d1ae73d4287f54ccfd420861a7b8c8f66f26caf218c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cWztXyP2p/8uo+H90aVIjQXPgeE7elrH5XISDwWuyigwpJpPF157pj3MUoJHXl0Dm/uDadjD+amJDt7iF5g+DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T04:16:44.824964Z","bundle_sha256":"bc622a13d76bb2fa72cab052dbcb848f9593544c90425850e5871e6edb047761"}}