{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5B6VZ757MME6R4OMF6H5KMQQVB","short_pith_number":"pith:5B6VZ757","canonical_record":{"source":{"id":"1810.11344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T14:22:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75b35fdb2af4ace5336987ba8b62de9b6f9f20c99f5e4e196ce5836d7c854687","abstract_canon_sha256":"e0c11410a25d637b6f39e59b753a75625b279d2dd230e6f10ac791252986fa29"},"schema_version":"1.0"},"canonical_sha256":"e87d5cffbf6309e8f1cc2f8fd53210a8736772893f8c8ceda286c63b492acdf7","source":{"kind":"arxiv","id":"1810.11344","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11344","created_at":"2026-05-18T00:02:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11344v1","created_at":"2026-05-18T00:02:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11344","created_at":"2026-05-18T00:02:14Z"},{"alias_kind":"pith_short_12","alias_value":"5B6VZ757MME6","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5B6VZ757MME6R4OM","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5B6VZ757","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5B6VZ757MME6R4OMF6H5KMQQVB","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T14:22:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"75b35fdb2af4ace5336987ba8b62de9b6f9f20c99f5e4e196ce5836d7c854687","abstract_canon_sha256":"e0c11410a25d637b6f39e59b753a75625b279d2dd230e6f10ac791252986fa29"},"schema_version":"1.0"},"canonical_sha256":"e87d5cffbf6309e8f1cc2f8fd53210a8736772893f8c8ceda286c63b492acdf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:14.430005Z","signature_b64":"pC9Vv1wMZiCtW5JHMdRcJc7Afe2DpFI8Tan93oTb3Tc1dwa23Myd3DI++CqjNlmnBnmgypde9uHTaG3/7pHOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e87d5cffbf6309e8f1cc2f8fd53210a8736772893f8c8ceda286c63b492acdf7","last_reissued_at":"2026-05-18T00:02:14.429226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:14.429226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11344","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":"2026-05-18T00:02:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CXsE3ofnjPmj2BTrT3Z8eDnnbg4oIvDAePH0mpT4LD75V65GsdUcDtzl4U5nbTcphuj2S6qhNK5TDmfD6iSZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:31:56.896106Z"},"content_sha256":"196835be0d248b26a7d701bace6beecab61e83d467c9ca01bbdc4e8a8647698c","schema_version":"1.0","event_id":"sha256:196835be0d248b26a7d701bace6beecab61e83d467c9ca01bbdc4e8a8647698c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5B6VZ757MME6R4OMF6H5KMQQVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benefits of over-parameterization with EM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arian Maleki, Daniel Hsu, Ji Xu","submitted_at":"2018-10-26T14:22:20Z","abstract_excerpt":"Expectation Maximization (EM) is among the most popular algorithms for maximum likelihood estimation, but it is generally only guaranteed to find its stationary points of the log-likelihood objective. The goal of this article is to present theoretical and empirical evidence that over-parameterization can help EM avoid spurious local optima in the log-likelihood. We consider the problem of estimating the mean vectors of a Gaussian mixture model in a scenario where the mixing weights are known. Our study shows that the global behavior of EM, when one uses an over-parameterized model in which the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11344","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":"2026-05-18T00:02:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ry20URW70FboMdKPZgDHNYdq/GT9IIbPk95Bnebh98yb7l5OA/AAh50Z3YzWLVXRqhwYhue5I6pBXbZpvq8GCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T22:31:56.896766Z"},"content_sha256":"5581d1480a9ac3d4b0828a1aadf52ce34ae2c7196238aa8b743bea07179a370a","schema_version":"1.0","event_id":"sha256:5581d1480a9ac3d4b0828a1aadf52ce34ae2c7196238aa8b743bea07179a370a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5B6VZ757MME6R4OMF6H5KMQQVB/bundle.json","state_url":"https://pith.science/pith/5B6VZ757MME6R4OMF6H5KMQQVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5B6VZ757MME6R4OMF6H5KMQQVB/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":"2026-05-30T22:31:56Z","links":{"resolver":"https://pith.science/pith/5B6VZ757MME6R4OMF6H5KMQQVB","bundle":"https://pith.science/pith/5B6VZ757MME6R4OMF6H5KMQQVB/bundle.json","state":"https://pith.science/pith/5B6VZ757MME6R4OMF6H5KMQQVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5B6VZ757MME6R4OMF6H5KMQQVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5B6VZ757MME6R4OMF6H5KMQQVB","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":"e0c11410a25d637b6f39e59b753a75625b279d2dd230e6f10ac791252986fa29","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T14:22:20Z","title_canon_sha256":"75b35fdb2af4ace5336987ba8b62de9b6f9f20c99f5e4e196ce5836d7c854687"},"schema_version":"1.0","source":{"id":"1810.11344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11344","created_at":"2026-05-18T00:02:14Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11344v1","created_at":"2026-05-18T00:02:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11344","created_at":"2026-05-18T00:02:14Z"},{"alias_kind":"pith_short_12","alias_value":"5B6VZ757MME6","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5B6VZ757MME6R4OM","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5B6VZ757","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:5581d1480a9ac3d4b0828a1aadf52ce34ae2c7196238aa8b743bea07179a370a","target":"graph","created_at":"2026-05-18T00:02:14Z","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":"Expectation Maximization (EM) is among the most popular algorithms for maximum likelihood estimation, but it is generally only guaranteed to find its stationary points of the log-likelihood objective. The goal of this article is to present theoretical and empirical evidence that over-parameterization can help EM avoid spurious local optima in the log-likelihood. We consider the problem of estimating the mean vectors of a Gaussian mixture model in a scenario where the mixing weights are known. Our study shows that the global behavior of EM, when one uses an over-parameterized model in which the","authors_text":"Arian Maleki, Daniel Hsu, Ji Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T14:22:20Z","title":"Benefits of over-parameterization with EM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11344","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":"sha256:196835be0d248b26a7d701bace6beecab61e83d467c9ca01bbdc4e8a8647698c","target":"record","created_at":"2026-05-18T00:02:14Z","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":"e0c11410a25d637b6f39e59b753a75625b279d2dd230e6f10ac791252986fa29","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T14:22:20Z","title_canon_sha256":"75b35fdb2af4ace5336987ba8b62de9b6f9f20c99f5e4e196ce5836d7c854687"},"schema_version":"1.0","source":{"id":"1810.11344","kind":"arxiv","version":1}},"canonical_sha256":"e87d5cffbf6309e8f1cc2f8fd53210a8736772893f8c8ceda286c63b492acdf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e87d5cffbf6309e8f1cc2f8fd53210a8736772893f8c8ceda286c63b492acdf7","first_computed_at":"2026-05-18T00:02:14.429226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:14.429226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pC9Vv1wMZiCtW5JHMdRcJc7Afe2DpFI8Tan93oTb3Tc1dwa23Myd3DI++CqjNlmnBnmgypde9uHTaG3/7pHOBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:14.430005Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:196835be0d248b26a7d701bace6beecab61e83d467c9ca01bbdc4e8a8647698c","sha256:5581d1480a9ac3d4b0828a1aadf52ce34ae2c7196238aa8b743bea07179a370a"],"state_sha256":"1be35dc5dcde8451cb14518de2886421177634a6386f66edf978a18b646c3be8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fb2gXrAGxjsLA036acZinoChwtP999o1N02TIloPCd1h7cWMVmidFj/7rUS4GK+GCUHDSCkDNw51MRM6JfBTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T22:31:56.901023Z","bundle_sha256":"a98aa6494bb96deab6f32ad3397e10f17c078030995569dffe13905e077eef3b"}}