{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Q6UPZZ55GVSPBWIH2X5WUL7B2H","short_pith_number":"pith:Q6UPZZ55","canonical_record":{"source":{"id":"1802.10418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-28T14:04:35Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"e39ebd5796e06388027840f637fa19d9a638ec5ffdda98a446b1c7b1df8d14d2","abstract_canon_sha256":"06ede88e50d7d04ed8f80e29f37e1b359ad41e6d312730c41ac9edbe007a36ae"},"schema_version":"1.0"},"canonical_sha256":"87a8fce7bd3564f0d907d5fb6a2fe1d1c788966fd334817880303686eaaa96a1","source":{"kind":"arxiv","id":"1802.10418","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10418","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10418v1","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10418","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"Q6UPZZ55GVSP","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6UPZZ55GVSPBWIH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6UPZZ55","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Q6UPZZ55GVSPBWIH2X5WUL7B2H","target":"record","payload":{"canonical_record":{"source":{"id":"1802.10418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-28T14:04:35Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"e39ebd5796e06388027840f637fa19d9a638ec5ffdda98a446b1c7b1df8d14d2","abstract_canon_sha256":"06ede88e50d7d04ed8f80e29f37e1b359ad41e6d312730c41ac9edbe007a36ae"},"schema_version":"1.0"},"canonical_sha256":"87a8fce7bd3564f0d907d5fb6a2fe1d1c788966fd334817880303686eaaa96a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:17.208362Z","signature_b64":"qUS7z6JBh3wjQXtrJCi0LNZ4nlSGKjPqEsT0i6q3IAvBq6p9q6J1a6KNxuT3MaHMvmwUkf1bU90DL05ByUA0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87a8fce7bd3564f0d907d5fb6a2fe1d1c788966fd334817880303686eaaa96a1","last_reissued_at":"2026-05-18T00:22:17.207641Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:17.207641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.10418","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":"2026-05-18T00:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PIaZV39/Q+ju+XQvv1GjiqZlW364U+NHOoWQGwQLrp8D+ZxYvmKhF2t4g5/uRs8/XgFPMaWOAV32ihDx03KBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:30:54.950492Z"},"content_sha256":"cd662f1983a111be0d12c23fe9d6b6cfbef02d64da51c2591905ade45230b43a","schema_version":"1.0","event_id":"sha256:cd662f1983a111be0d12c23fe9d6b6cfbef02d64da51c2591905ade45230b43a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Q6UPZZ55GVSPBWIH2X5WUL7B2H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"math.OC","authors_text":"Mingyi Hong, Songtao Lu, Zhengdao Wang","submitted_at":"2018-02-28T14:04:35Z","abstract_excerpt":"The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc. The algorithm updates two blocks of variables in an alternating manner, in which a gradient step is taken on one block, while keeping the remaining block fixed. When the objective function is nonconvex, it is well-known the AGD converges to the first-order stationary solution with a global sublinear rate.\n  In this paper, we show that a variant of AGD-type algorithms will not be trapped by \"bad\" stationary solution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10418","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":"2026-05-18T00:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dtqkUSaS6jjZa1efzXZFhCAarAnPiSrHHfDYg3LkA6G9mN9jTM0TkjxjLis0dxyzezD/LVVy+f529rmGCIQHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:30:54.950842Z"},"content_sha256":"1d713d41b50a1bd1752e12439b470a180681df306187d0380dcb382a9c1d6549","schema_version":"1.0","event_id":"sha256:1d713d41b50a1bd1752e12439b470a180681df306187d0380dcb382a9c1d6549"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6UPZZ55GVSPBWIH2X5WUL7B2H/bundle.json","state_url":"https://pith.science/pith/Q6UPZZ55GVSPBWIH2X5WUL7B2H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6UPZZ55GVSPBWIH2X5WUL7B2H/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":"2026-06-26T16:30:54Z","links":{"resolver":"https://pith.science/pith/Q6UPZZ55GVSPBWIH2X5WUL7B2H","bundle":"https://pith.science/pith/Q6UPZZ55GVSPBWIH2X5WUL7B2H/bundle.json","state":"https://pith.science/pith/Q6UPZZ55GVSPBWIH2X5WUL7B2H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6UPZZ55GVSPBWIH2X5WUL7B2H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Q6UPZZ55GVSPBWIH2X5WUL7B2H","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":"06ede88e50d7d04ed8f80e29f37e1b359ad41e6d312730c41ac9edbe007a36ae","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-28T14:04:35Z","title_canon_sha256":"e39ebd5796e06388027840f637fa19d9a638ec5ffdda98a446b1c7b1df8d14d2"},"schema_version":"1.0","source":{"id":"1802.10418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10418","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10418v1","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10418","created_at":"2026-05-18T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"Q6UPZZ55GVSP","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6UPZZ55GVSPBWIH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6UPZZ55","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:1d713d41b50a1bd1752e12439b470a180681df306187d0380dcb382a9c1d6549","target":"graph","created_at":"2026-05-18T00:22:17Z","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":"The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc. The algorithm updates two blocks of variables in an alternating manner, in which a gradient step is taken on one block, while keeping the remaining block fixed. When the objective function is nonconvex, it is well-known the AGD converges to the first-order stationary solution with a global sublinear rate.\n  In this paper, we show that a variant of AGD-type algorithms will not be trapped by \"bad\" stationary solution","authors_text":"Mingyi Hong, Songtao Lu, Zhengdao Wang","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-28T14:04:35Z","title":"On the Sublinear Convergence of Randomly Perturbed Alternating Gradient Descent to Second Order Stationary Solutions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10418","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:cd662f1983a111be0d12c23fe9d6b6cfbef02d64da51c2591905ade45230b43a","target":"record","created_at":"2026-05-18T00:22:17Z","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":"06ede88e50d7d04ed8f80e29f37e1b359ad41e6d312730c41ac9edbe007a36ae","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-28T14:04:35Z","title_canon_sha256":"e39ebd5796e06388027840f637fa19d9a638ec5ffdda98a446b1c7b1df8d14d2"},"schema_version":"1.0","source":{"id":"1802.10418","kind":"arxiv","version":1}},"canonical_sha256":"87a8fce7bd3564f0d907d5fb6a2fe1d1c788966fd334817880303686eaaa96a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87a8fce7bd3564f0d907d5fb6a2fe1d1c788966fd334817880303686eaaa96a1","first_computed_at":"2026-05-18T00:22:17.207641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:17.207641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qUS7z6JBh3wjQXtrJCi0LNZ4nlSGKjPqEsT0i6q3IAvBq6p9q6J1a6KNxuT3MaHMvmwUkf1bU90DL05ByUA0Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:17.208362Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.10418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd662f1983a111be0d12c23fe9d6b6cfbef02d64da51c2591905ade45230b43a","sha256:1d713d41b50a1bd1752e12439b470a180681df306187d0380dcb382a9c1d6549"],"state_sha256":"f25760f9b17530ff82f7bac7fd8e950f11b378fe597f7a566f54fd6841e790b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qrF/kJxxl6uZHtcv5AsqRc+xGsK+YIGcMzccXx8NmoRjfLjllRPOTTNVJCUIhf6+BMBAEgLi8BYuoefB/b67DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T16:30:54.952837Z","bundle_sha256":"3a7adccada7e2bdecee6366f535130cc2d1c289b5df3a0f28eaab9605c3a8ad5"}}