{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OKH63T7IG22DKRAWRFNOQT3NQV","short_pith_number":"pith:OKH63T7I","canonical_record":{"source":{"id":"1802.04617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T13:37:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"617adc727d3c3e16fb12f6d3404b09254c4c2af6e19e75d118512be0126a539d","abstract_canon_sha256":"9787eb0451c955a65604b1808c5b16aa01257b5d3445d214f69cd71433096541"},"schema_version":"1.0"},"canonical_sha256":"728fedcfe836b4354416895ae84f6d857487985cba040d856bd0b117c5fcd00d","source":{"kind":"arxiv","id":"1802.04617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04617","created_at":"2026-05-18T00:23:41Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04617v1","created_at":"2026-05-18T00:23:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04617","created_at":"2026-05-18T00:23:41Z"},{"alias_kind":"pith_short_12","alias_value":"OKH63T7IG22D","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OKH63T7IG22DKRAW","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OKH63T7I","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OKH63T7IG22DKRAWRFNOQT3NQV","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T13:37:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"617adc727d3c3e16fb12f6d3404b09254c4c2af6e19e75d118512be0126a539d","abstract_canon_sha256":"9787eb0451c955a65604b1808c5b16aa01257b5d3445d214f69cd71433096541"},"schema_version":"1.0"},"canonical_sha256":"728fedcfe836b4354416895ae84f6d857487985cba040d856bd0b117c5fcd00d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:41.942838Z","signature_b64":"SVK6XPcndrRIWsPJvhOZgMJSW8gOJn3ZVcOu+sjmDuTci6GdZluZrdntdlm48cnraDc2XczKOAQLyiRI3jWtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"728fedcfe836b4354416895ae84f6d857487985cba040d856bd0b117c5fcd00d","last_reissued_at":"2026-05-18T00:23:41.942079Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:41.942079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04617","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":"2026-05-18T00:23:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KrUabGFaMSl2CkaJvzMTGHPkcqJi0aAydJGuz7VY0/pJNmOrUI+zzuBostHShDiZk9jchl2QiTgCkDdsfzaoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:00:22.648341Z"},"content_sha256":"2426e107ab43f574c47ca14f486ce86458fa698599fa42664a1a8580704399e5","schema_version":"1.0","event_id":"sha256:2426e107ab43f574c47ca14f486ce86458fa698599fa42664a1a8580704399e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OKH63T7IG22DKRAWRFNOQT3NQV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Global Convergence via Landscape of Empirical Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chao Qu, Huan Xu, Yan Li","submitted_at":"2018-02-13T13:37:11Z","abstract_excerpt":"While optimizing convex objective (loss) functions has been a powerhouse for machine learning for at least two decades, non-convex loss functions have attracted fast growing interests recently, due to many desirable properties such as superior robustness and classification accuracy, compared with their convex counterparts. The main obstacle for non-convex estimators is that it is in general intractable to find the optimal solution. In this paper, we study the computational issues for some non-convex M-estimators. In particular, we show that the stochastic variance reduction methods converge to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04617","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":"2026-05-18T00:23:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xqbmmjAGl4Y8RcAhN+CNoLrWNylF4IlsL8eSx79FfxhabfS79/JXmDUS/uoXv1E+72cqpYiLbOE+4Z2L5CDhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:00:22.649122Z"},"content_sha256":"c19f6240703c9656e52e7a8e58e5c225475d5aaebc871d7131b6faa7a513a921","schema_version":"1.0","event_id":"sha256:c19f6240703c9656e52e7a8e58e5c225475d5aaebc871d7131b6faa7a513a921"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKH63T7IG22DKRAWRFNOQT3NQV/bundle.json","state_url":"https://pith.science/pith/OKH63T7IG22DKRAWRFNOQT3NQV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKH63T7IG22DKRAWRFNOQT3NQV/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":"2026-05-31T01:00:22Z","links":{"resolver":"https://pith.science/pith/OKH63T7IG22DKRAWRFNOQT3NQV","bundle":"https://pith.science/pith/OKH63T7IG22DKRAWRFNOQT3NQV/bundle.json","state":"https://pith.science/pith/OKH63T7IG22DKRAWRFNOQT3NQV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKH63T7IG22DKRAWRFNOQT3NQV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OKH63T7IG22DKRAWRFNOQT3NQV","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":"9787eb0451c955a65604b1808c5b16aa01257b5d3445d214f69cd71433096541","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T13:37:11Z","title_canon_sha256":"617adc727d3c3e16fb12f6d3404b09254c4c2af6e19e75d118512be0126a539d"},"schema_version":"1.0","source":{"id":"1802.04617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04617","created_at":"2026-05-18T00:23:41Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04617v1","created_at":"2026-05-18T00:23:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04617","created_at":"2026-05-18T00:23:41Z"},{"alias_kind":"pith_short_12","alias_value":"OKH63T7IG22D","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OKH63T7IG22DKRAW","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OKH63T7I","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:c19f6240703c9656e52e7a8e58e5c225475d5aaebc871d7131b6faa7a513a921","target":"graph","created_at":"2026-05-18T00:23:41Z","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":"While optimizing convex objective (loss) functions has been a powerhouse for machine learning for at least two decades, non-convex loss functions have attracted fast growing interests recently, due to many desirable properties such as superior robustness and classification accuracy, compared with their convex counterparts. The main obstacle for non-convex estimators is that it is in general intractable to find the optimal solution. In this paper, we study the computational issues for some non-convex M-estimators. In particular, we show that the stochastic variance reduction methods converge to","authors_text":"Chao Qu, Huan Xu, Yan Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T13:37:11Z","title":"Fast Global Convergence via Landscape of Empirical Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04617","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":"sha256:2426e107ab43f574c47ca14f486ce86458fa698599fa42664a1a8580704399e5","target":"record","created_at":"2026-05-18T00:23:41Z","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":"9787eb0451c955a65604b1808c5b16aa01257b5d3445d214f69cd71433096541","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-13T13:37:11Z","title_canon_sha256":"617adc727d3c3e16fb12f6d3404b09254c4c2af6e19e75d118512be0126a539d"},"schema_version":"1.0","source":{"id":"1802.04617","kind":"arxiv","version":1}},"canonical_sha256":"728fedcfe836b4354416895ae84f6d857487985cba040d856bd0b117c5fcd00d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"728fedcfe836b4354416895ae84f6d857487985cba040d856bd0b117c5fcd00d","first_computed_at":"2026-05-18T00:23:41.942079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:41.942079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SVK6XPcndrRIWsPJvhOZgMJSW8gOJn3ZVcOu+sjmDuTci6GdZluZrdntdlm48cnraDc2XczKOAQLyiRI3jWtDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:41.942838Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2426e107ab43f574c47ca14f486ce86458fa698599fa42664a1a8580704399e5","sha256:c19f6240703c9656e52e7a8e58e5c225475d5aaebc871d7131b6faa7a513a921"],"state_sha256":"f4b0874d18e76e376dc11804030fb556ebe5f661acc97562ce2cbb62dcdd3e78"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q+jK5jxcj21m/fV0Awv2hKnlT1Gj94ed1UyW3WXVgJ91AnbPbIPF2L7R/gyBlRFuJkGF9rrcxaTLwkk5f/9FCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:00:22.653231Z","bundle_sha256":"17aef106b657cad2ae86b2a0cb96a9a46838b8ee894801814f2b7e2eb713e3cb"}}