{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:53Z2OEUHKPN2IKWOJPMJBVN47U","short_pith_number":"pith:53Z2OEUH","canonical_record":{"source":{"id":"1711.10467","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T18:53:38Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"172a18396b97540c2ac81e0ab09f2e5603b39f2a741637c2f1029d13127f65e2","abstract_canon_sha256":"f1265fd6871cc5a13365f93ab36a08ab97bf7d9c5863972d3cb3636e99f5e417"},"schema_version":"1.0"},"canonical_sha256":"eef3a7128753dba42ace4bd890d5bcfd1dad39cfc9653bf0b1cc4d25f9f58737","source":{"kind":"arxiv","id":"1711.10467","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.10467","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"1711.10467v3","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10467","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"53Z2OEUHKPN2","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"53Z2OEUHKPN2IKWO","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"53Z2OEUH","created_at":"2026-07-05T01:08:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:53Z2OEUHKPN2IKWOJPMJBVN47U","target":"record","payload":{"canonical_record":{"source":{"id":"1711.10467","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T18:53:38Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"172a18396b97540c2ac81e0ab09f2e5603b39f2a741637c2f1029d13127f65e2","abstract_canon_sha256":"f1265fd6871cc5a13365f93ab36a08ab97bf7d9c5863972d3cb3636e99f5e417"},"schema_version":"1.0"},"canonical_sha256":"eef3a7128753dba42ace4bd890d5bcfd1dad39cfc9653bf0b1cc4d25f9f58737","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:20.872770Z","signature_b64":"nKHoO4vKtjHZX7RiBlbwbQNup2J3bctyJ9jfo/Q5HfFktzb6+SIc62eQkpP6Of69w+ZhL2TDFybnP4FWsC5vAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eef3a7128753dba42ace4bd890d5bcfd1dad39cfc9653bf0b1cc4d25f9f58737","last_reissued_at":"2026-07-05T01:08:20.872327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:20.872327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.10467","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bfRDVCe5IBtqUuxw8Q9C+heOjNDeyLOYIK0/ukUxQKVecb3cNz/7FX38ddxDvm1PO+nZkNVzmLOxxj7vcULfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:16:53.110001Z"},"content_sha256":"8f8ca634a0d74585c0248d3f5bb73c9df1c71ea55278256f64115e58ae6b004c","schema_version":"1.0","event_id":"sha256:8f8ca634a0d74585c0248d3f5bb73c9df1c71ea55278256f64115e58ae6b004c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:53Z2OEUHKPN2IKWOJPMJBVN47U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Cong Ma, Kaizheng Wang, Yuejie Chi, Yuxin Chen","submitted_at":"2017-11-28T18:53:38Z","abstract_excerpt":"Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art procedures often require proper regularization (e.g. trimming, regularized cost, projection) in order to guarantee fast convergence. For vanilla procedures such as gradient descent, however, prior theory either recommends highly conservative learning rates to avoid overshooting, or completely lacks performance guarantees.\n  This paper uncovers a striking phenomenon in nonconvex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10467","kind":"arxiv","version":3},"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/1711.10467/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":"2026-07-05T01:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xo6ZNPETBPs5bJLHQWn/A6vigp03ifZkiQkvslZ/E4XzfcWpw7iqDuvnbBCPiVRHS5y2zbr4MOUEUIgvbiYCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:16:53.110737Z"},"content_sha256":"3e679ab671bc11a4ce72a392c5099dd2a0d1c6b9351ea2fdb70e1558ba49bf93","schema_version":"1.0","event_id":"sha256:3e679ab671bc11a4ce72a392c5099dd2a0d1c6b9351ea2fdb70e1558ba49bf93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53Z2OEUHKPN2IKWOJPMJBVN47U/bundle.json","state_url":"https://pith.science/pith/53Z2OEUHKPN2IKWOJPMJBVN47U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53Z2OEUHKPN2IKWOJPMJBVN47U/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":"2026-08-16T10:16:53Z","links":{"resolver":"https://pith.science/pith/53Z2OEUHKPN2IKWOJPMJBVN47U","bundle":"https://pith.science/pith/53Z2OEUHKPN2IKWOJPMJBVN47U/bundle.json","state":"https://pith.science/pith/53Z2OEUHKPN2IKWOJPMJBVN47U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53Z2OEUHKPN2IKWOJPMJBVN47U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:53Z2OEUHKPN2IKWOJPMJBVN47U","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":"f1265fd6871cc5a13365f93ab36a08ab97bf7d9c5863972d3cb3636e99f5e417","cross_cats_sorted":["cs.IT","math.IT","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T18:53:38Z","title_canon_sha256":"172a18396b97540c2ac81e0ab09f2e5603b39f2a741637c2f1029d13127f65e2"},"schema_version":"1.0","source":{"id":"1711.10467","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.10467","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"1711.10467v3","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10467","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"53Z2OEUHKPN2","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"53Z2OEUHKPN2IKWO","created_at":"2026-07-05T01:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"53Z2OEUH","created_at":"2026-07-05T01:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:3e679ab671bc11a4ce72a392c5099dd2a0d1c6b9351ea2fdb70e1558ba49bf93","target":"graph","created_at":"2026-07-05T01:08:20Z","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/1711.10467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art procedures often require proper regularization (e.g. trimming, regularized cost, projection) in order to guarantee fast convergence. For vanilla procedures such as gradient descent, however, prior theory either recommends highly conservative learning rates to avoid overshooting, or completely lacks performance guarantees.\n  This paper uncovers a striking phenomenon in nonconvex ","authors_text":"Cong Ma, Kaizheng Wang, Yuejie Chi, Yuxin Chen","cross_cats":["cs.IT","math.IT","math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T18:53:38Z","title":"Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10467","kind":"arxiv","version":3},"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":"sha256:8f8ca634a0d74585c0248d3f5bb73c9df1c71ea55278256f64115e58ae6b004c","target":"record","created_at":"2026-07-05T01:08:20Z","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":"f1265fd6871cc5a13365f93ab36a08ab97bf7d9c5863972d3cb3636e99f5e417","cross_cats_sorted":["cs.IT","math.IT","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T18:53:38Z","title_canon_sha256":"172a18396b97540c2ac81e0ab09f2e5603b39f2a741637c2f1029d13127f65e2"},"schema_version":"1.0","source":{"id":"1711.10467","kind":"arxiv","version":3}},"canonical_sha256":"eef3a7128753dba42ace4bd890d5bcfd1dad39cfc9653bf0b1cc4d25f9f58737","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eef3a7128753dba42ace4bd890d5bcfd1dad39cfc9653bf0b1cc4d25f9f58737","first_computed_at":"2026-07-05T01:08:20.872327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:20.872327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nKHoO4vKtjHZX7RiBlbwbQNup2J3bctyJ9jfo/Q5HfFktzb6+SIc62eQkpP6Of69w+ZhL2TDFybnP4FWsC5vAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:20.872770Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.10467","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f8ca634a0d74585c0248d3f5bb73c9df1c71ea55278256f64115e58ae6b004c","sha256:3e679ab671bc11a4ce72a392c5099dd2a0d1c6b9351ea2fdb70e1558ba49bf93"],"state_sha256":"527b997854b63e15a3491c9fce1bf4ea6b80c54cdf2c50e8604d39c145248b47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUd92J8YxcJatyTPJUFep5b8sX4URBUOaRzKyqc50Mul4g/0rVb/F5/uPBEeA6IZDiNG6nlSAtZbwuvyMHSYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:16:53.116248Z","bundle_sha256":"5cc18ff2289289006fe3094a91a42bfc8b56377494338e04743bec545837cb79"}}