{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ODOYAM4EBXZ7UTDDSY2KTSF35Y","short_pith_number":"pith:ODOYAM4E","schema_version":"1.0","canonical_sha256":"70dd8033840df3fa4c639634a9c8bbee163da3bfecfd8c2ddee6edb8909a6892","source":{"kind":"arxiv","id":"1912.09379","version":3},"attestation_state":"computed","paper":{"title":"Gradient-based training of Gaussian Mixture Models for High-Dimensional Streaming Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Gepperth, Benedikt Pf\\\"ulb","submitted_at":"2019-12-18T09:35:39Z","abstract_excerpt":"We present an approach for efficiently training Gaussian Mixture Model (GMM) by Stochastic Gradient Descent (SGD) with non-stationary, high-dimensional streaming data. Our training scheme does not require data-driven parameter initialization (e.g., k-means) and can thus be trained based on a random initialization. Furthermore, the approach allows mini-batch sizes as low as 1, which are typical for streaming-data settings. Major problems in such settings are undesirable local optima during early training phases and numerical instabilities due to high data dimensionalities. We introduce an adapt"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.09379","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-18T09:35:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9583372bb1efa833fd2cecf78a5a2531ddd11ba9b8132494cec0243910f5b3e0","abstract_canon_sha256":"d83cbe09cbf0e54793d53f7c99a8bf5c7d5ba627d9c39799da47825bfde8fb02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:27.938305Z","signature_b64":"71mpEVkpzqIzBRJvmJNBQTpph5ek+MyC+AFA3jv9jPWE6n40NtNSiDB1kvPGFvSxymcS8NWwDICPXPH6RvZnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70dd8033840df3fa4c639634a9c8bbee163da3bfecfd8c2ddee6edb8909a6892","last_reissued_at":"2026-07-05T02:54:27.937835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:27.937835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient-based training of Gaussian Mixture Models for High-Dimensional Streaming Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Gepperth, Benedikt Pf\\\"ulb","submitted_at":"2019-12-18T09:35:39Z","abstract_excerpt":"We present an approach for efficiently training Gaussian Mixture Model (GMM) by Stochastic Gradient Descent (SGD) with non-stationary, high-dimensional streaming data. Our training scheme does not require data-driven parameter initialization (e.g., k-means) and can thus be trained based on a random initialization. Furthermore, the approach allows mini-batch sizes as low as 1, which are typical for streaming-data settings. Major problems in such settings are undesirable local optima during early training phases and numerical instabilities due to high data dimensionalities. We introduce an adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.09379","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/1912.09379/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.09379","created_at":"2026-07-05T02:54:27.937894+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.09379v3","created_at":"2026-07-05T02:54:27.937894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.09379","created_at":"2026-07-05T02:54:27.937894+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODOYAM4EBXZ7","created_at":"2026-07-05T02:54:27.937894+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODOYAM4EBXZ7UTDD","created_at":"2026-07-05T02:54:27.937894+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODOYAM4E","created_at":"2026-07-05T02:54:27.937894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03029","citing_title":"Extreme Deconvolution Reimagined: Conditional Densities via Neural Networks and an Application in Quasar Classification","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y","json":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y.json","graph_json":"https://pith.science/api/pith-number/ODOYAM4EBXZ7UTDDSY2KTSF35Y/graph.json","events_json":"https://pith.science/api/pith-number/ODOYAM4EBXZ7UTDDSY2KTSF35Y/events.json","paper":"https://pith.science/paper/ODOYAM4E"},"agent_actions":{"view_html":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y","download_json":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y.json","view_paper":"https://pith.science/paper/ODOYAM4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.09379&json=true","fetch_graph":"https://pith.science/api/pith-number/ODOYAM4EBXZ7UTDDSY2KTSF35Y/graph.json","fetch_events":"https://pith.science/api/pith-number/ODOYAM4EBXZ7UTDDSY2KTSF35Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y/action/storage_attestation","attest_author":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y/action/author_attestation","sign_citation":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y/action/citation_signature","submit_replication":"https://pith.science/pith/ODOYAM4EBXZ7UTDDSY2KTSF35Y/action/replication_record"}},"created_at":"2026-07-05T02:54:27.937894+00:00","updated_at":"2026-07-05T02:54:27.937894+00:00"}