{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MWHTHAGXELQV3KYUNHDYPXSPAM","short_pith_number":"pith:MWHTHAGX","canonical_record":{"source":{"id":"1912.02427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T08:14:24Z","cross_cats_sorted":["cs.IT","eess.SP","math.IT","math.OC","stat.ML"],"title_canon_sha256":"1f02abeae68d6078475f25cdf15c4b0cc59ec8ac16f8d3411643f5b568250cc1","abstract_canon_sha256":"8613775588fa6deb882df0d8aaa6b50f3c9ff337a13e9ad7e56508fc14901d95"},"schema_version":"1.0"},"canonical_sha256":"658f3380d722e15dab1469c787de4f030f530c29906719cde25ef5a5f09010ad","source":{"kind":"arxiv","id":"1912.02427","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02427","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02427v2","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02427","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"pith_short_12","alias_value":"MWHTHAGXELQV","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"pith_short_16","alias_value":"MWHTHAGXELQV3KYU","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"pith_short_8","alias_value":"MWHTHAGX","created_at":"2026-07-05T00:25:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MWHTHAGXELQV3KYUNHDYPXSPAM","target":"record","payload":{"canonical_record":{"source":{"id":"1912.02427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T08:14:24Z","cross_cats_sorted":["cs.IT","eess.SP","math.IT","math.OC","stat.ML"],"title_canon_sha256":"1f02abeae68d6078475f25cdf15c4b0cc59ec8ac16f8d3411643f5b568250cc1","abstract_canon_sha256":"8613775588fa6deb882df0d8aaa6b50f3c9ff337a13e9ad7e56508fc14901d95"},"schema_version":"1.0"},"canonical_sha256":"658f3380d722e15dab1469c787de4f030f530c29906719cde25ef5a5f09010ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:19.788414Z","signature_b64":"mW6sOf+M6zq/OIfkXUIbf3ARBYhgypI6elLqLL4PXbZ2m83jwopOBb4W10lTFial6DlF6MtOEZMyu5jvdx5tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"658f3380d722e15dab1469c787de4f030f530c29906719cde25ef5a5f09010ad","last_reissued_at":"2026-07-05T00:25:19.788039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:19.788039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.02427","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:25:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2lZDgrv83YxyOp2r2b1pGwad7rahGwJL//q6KZh+zRSRB9ush/nBdix2WsnnOhsN3z5yyg/TiVKYuxdj94VCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:55:42.573521Z"},"content_sha256":"422861fecb16dea761380c87bfaab301f467930881cd69912038091e02a4b339","schema_version":"1.0","event_id":"sha256:422861fecb16dea761380c87bfaab301f467930881cd69912038091e02a4b339"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MWHTHAGXELQV3KYUNHDYPXSPAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analysis of the Optimization Landscapes for Overcomplete Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","eess.SP","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qing Qu, Xiao Li, Yuexiang Zhai, Yuqian Zhang, Zhihui Zhu","submitted_at":"2019-12-05T08:14:24Z","abstract_excerpt":"We study nonconvex optimization landscapes for learning overcomplete representations, including learning (i) sparsely used overcomplete dictionaries and (ii) convolutional dictionaries, where these unsupervised learning problems find many applications in high-dimensional data analysis. Despite the empirical success of simple nonconvex algorithms, theoretical justifications of why these methods work so well are far from satisfactory. In this work, we show these problems can be formulated as $\\ell^4$-norm optimization problems with spherical constraint, and study the geometric properties of thei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02427","kind":"arxiv","version":2},"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/1912.02427/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":"2026-07-05T00:25:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tfLXM7C4quXS5Kh80E50Tsi1yiBMePuOwtScysvpRotKtNM+tG4cWjONwkj+DT/DMzk7sSBPtqOJHqIlZT7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:55:42.574347Z"},"content_sha256":"089fe8f7093c66e1f3a6f5b1f430b0d2b3e4522db5b8f03dca576792d78d6c66","schema_version":"1.0","event_id":"sha256:089fe8f7093c66e1f3a6f5b1f430b0d2b3e4522db5b8f03dca576792d78d6c66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWHTHAGXELQV3KYUNHDYPXSPAM/bundle.json","state_url":"https://pith.science/pith/MWHTHAGXELQV3KYUNHDYPXSPAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWHTHAGXELQV3KYUNHDYPXSPAM/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":"2026-08-07T20:55:42Z","links":{"resolver":"https://pith.science/pith/MWHTHAGXELQV3KYUNHDYPXSPAM","bundle":"https://pith.science/pith/MWHTHAGXELQV3KYUNHDYPXSPAM/bundle.json","state":"https://pith.science/pith/MWHTHAGXELQV3KYUNHDYPXSPAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWHTHAGXELQV3KYUNHDYPXSPAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MWHTHAGXELQV3KYUNHDYPXSPAM","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":"8613775588fa6deb882df0d8aaa6b50f3c9ff337a13e9ad7e56508fc14901d95","cross_cats_sorted":["cs.IT","eess.SP","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T08:14:24Z","title_canon_sha256":"1f02abeae68d6078475f25cdf15c4b0cc59ec8ac16f8d3411643f5b568250cc1"},"schema_version":"1.0","source":{"id":"1912.02427","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.02427","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"arxiv_version","alias_value":"1912.02427v2","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02427","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"pith_short_12","alias_value":"MWHTHAGXELQV","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"pith_short_16","alias_value":"MWHTHAGXELQV3KYU","created_at":"2026-07-05T00:25:19Z"},{"alias_kind":"pith_short_8","alias_value":"MWHTHAGX","created_at":"2026-07-05T00:25:19Z"}],"graph_snapshots":[{"event_id":"sha256:089fe8f7093c66e1f3a6f5b1f430b0d2b3e4522db5b8f03dca576792d78d6c66","target":"graph","created_at":"2026-07-05T00:25:19Z","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/1912.02427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study nonconvex optimization landscapes for learning overcomplete representations, including learning (i) sparsely used overcomplete dictionaries and (ii) convolutional dictionaries, where these unsupervised learning problems find many applications in high-dimensional data analysis. Despite the empirical success of simple nonconvex algorithms, theoretical justifications of why these methods work so well are far from satisfactory. In this work, we show these problems can be formulated as $\\ell^4$-norm optimization problems with spherical constraint, and study the geometric properties of thei","authors_text":"Qing Qu, Xiao Li, Yuexiang Zhai, Yuqian Zhang, Zhihui Zhu","cross_cats":["cs.IT","eess.SP","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T08:14:24Z","title":"Analysis of the Optimization Landscapes for Overcomplete Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02427","kind":"arxiv","version":2},"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":"sha256:422861fecb16dea761380c87bfaab301f467930881cd69912038091e02a4b339","target":"record","created_at":"2026-07-05T00:25:19Z","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":"8613775588fa6deb882df0d8aaa6b50f3c9ff337a13e9ad7e56508fc14901d95","cross_cats_sorted":["cs.IT","eess.SP","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T08:14:24Z","title_canon_sha256":"1f02abeae68d6078475f25cdf15c4b0cc59ec8ac16f8d3411643f5b568250cc1"},"schema_version":"1.0","source":{"id":"1912.02427","kind":"arxiv","version":2}},"canonical_sha256":"658f3380d722e15dab1469c787de4f030f530c29906719cde25ef5a5f09010ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"658f3380d722e15dab1469c787de4f030f530c29906719cde25ef5a5f09010ad","first_computed_at":"2026-07-05T00:25:19.788039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:19.788039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mW6sOf+M6zq/OIfkXUIbf3ARBYhgypI6elLqLL4PXbZ2m83jwopOBb4W10lTFial6DlF6MtOEZMyu5jvdx5tCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:19.788414Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.02427","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:422861fecb16dea761380c87bfaab301f467930881cd69912038091e02a4b339","sha256:089fe8f7093c66e1f3a6f5b1f430b0d2b3e4522db5b8f03dca576792d78d6c66"],"state_sha256":"1ed260039fe8ce342e5a8fcfd8de15ce946811ba2a3261bd64f8adbb76fceb68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"go3YcPy1SzW19Tl3EReXzTrqM9ULJofVRHkRLlIBECymjpJNpKD8b1qBxfnru9cd5i9JrU0kg+4YcsEOhClFDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:55:42.581567Z","bundle_sha256":"144e7c5f373e5882986a3cb057c064ba32d65bcae9514df5924079f03a299d6c"}}