{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:55RDTRO7ZBFNKDQHW5WAFB56JN","short_pith_number":"pith:55RDTRO7","canonical_record":{"source":{"id":"1803.09357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T22:18:04Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a32886221f076c46938a79ef71a80c947e0932158e8c08f1768986b8e0e621ea","abstract_canon_sha256":"d9384ef8b7b2978e0dd297d8d2234b9786cdc1ae773f4f0e5e034959f538ab4f"},"schema_version":"1.0"},"canonical_sha256":"ef6239c5dfc84ad50e07b76c0287be4b61c008672fd20bd00fc999a5b7570411","source":{"kind":"arxiv","id":"1803.09357","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09357","created_at":"2026-05-18T00:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09357v2","created_at":"2026-05-18T00:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09357","created_at":"2026-05-18T00:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"55RDTRO7ZBFN","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"55RDTRO7ZBFNKDQH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"55RDTRO7","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:55RDTRO7ZBFNKDQHW5WAFB56JN","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T22:18:04Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a32886221f076c46938a79ef71a80c947e0932158e8c08f1768986b8e0e621ea","abstract_canon_sha256":"d9384ef8b7b2978e0dd297d8d2234b9786cdc1ae773f4f0e5e034959f538ab4f"},"schema_version":"1.0"},"canonical_sha256":"ef6239c5dfc84ad50e07b76c0287be4b61c008672fd20bd00fc999a5b7570411","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:55.010101Z","signature_b64":"SvCaVBDMIBEcgdIfCDxnVkXFRDV/atIVkEihLbVURdAPCVwNwUFMfcNSuKD2rit44sy3ya4wQwi02VrrWdiYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef6239c5dfc84ad50e07b76c0287be4b61c008672fd20bd00fc999a5b7570411","last_reissued_at":"2026-05-18T00:02:55.009432Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:55.009432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09357","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":"2026-05-18T00:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UyeIvPpZouXh0pM72/7n9MWC4JVfVVO98nLCBjRIByOoIe+zEHQw+c2Y92kNuYo7p6JAhZfHAZpyDMepVHtcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:35:27.957568Z"},"content_sha256":"7d36ac3d6e958e9a06fe0f023254be1cb060df8da9e0fca368d945235e187303","schema_version":"1.0","event_id":"sha256:7d36ac3d6e958e9a06fe0f023254be1cb060df8da9e0fca368d945235e187303"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:55RDTRO7ZBFNKDQHW5WAFB56JN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Local Minima of the Empirical Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Lydia T. Liu, Michael I. Jordan, Rong Ge","submitted_at":"2018-03-25T22:18:04Z","abstract_excerpt":"Population risk is always of primary interest in machine learning; however, learning algorithms only have access to the empirical risk. Even for applications with nonconvex nonsmooth losses (such as modern deep networks), the population risk is generally significantly more well-behaved from an optimization point of view than the empirical risk. In particular, sampling can create many spurious local minima. We consider a general framework which aims to optimize a smooth nonconvex function $F$ (population risk) given only access to an approximation $f$ (empirical risk) that is pointwise close to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09357","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":""},"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":"2026-05-18T00:02:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fx3ps23dkFThkseWWLXDqLnonjLPl0qwWz7dgT4aw4aq0JU5+JqdSSSP/Vyq/anCRV1zliSqmZTAwZFPV0cUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T10:35:27.957916Z"},"content_sha256":"2a29319f41dee93e5c18e66b8013b5d5839fb363b752215ddd901d3cdcf200c1","schema_version":"1.0","event_id":"sha256:2a29319f41dee93e5c18e66b8013b5d5839fb363b752215ddd901d3cdcf200c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55RDTRO7ZBFNKDQHW5WAFB56JN/bundle.json","state_url":"https://pith.science/pith/55RDTRO7ZBFNKDQHW5WAFB56JN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55RDTRO7ZBFNKDQHW5WAFB56JN/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":"2026-06-04T10:35:27Z","links":{"resolver":"https://pith.science/pith/55RDTRO7ZBFNKDQHW5WAFB56JN","bundle":"https://pith.science/pith/55RDTRO7ZBFNKDQHW5WAFB56JN/bundle.json","state":"https://pith.science/pith/55RDTRO7ZBFNKDQHW5WAFB56JN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55RDTRO7ZBFNKDQHW5WAFB56JN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:55RDTRO7ZBFNKDQHW5WAFB56JN","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":"d9384ef8b7b2978e0dd297d8d2234b9786cdc1ae773f4f0e5e034959f538ab4f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T22:18:04Z","title_canon_sha256":"a32886221f076c46938a79ef71a80c947e0932158e8c08f1768986b8e0e621ea"},"schema_version":"1.0","source":{"id":"1803.09357","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09357","created_at":"2026-05-18T00:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09357v2","created_at":"2026-05-18T00:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09357","created_at":"2026-05-18T00:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"55RDTRO7ZBFN","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"55RDTRO7ZBFNKDQH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"55RDTRO7","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:2a29319f41dee93e5c18e66b8013b5d5839fb363b752215ddd901d3cdcf200c1","target":"graph","created_at":"2026-05-18T00:02:55Z","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":"Population risk is always of primary interest in machine learning; however, learning algorithms only have access to the empirical risk. Even for applications with nonconvex nonsmooth losses (such as modern deep networks), the population risk is generally significantly more well-behaved from an optimization point of view than the empirical risk. In particular, sampling can create many spurious local minima. We consider a general framework which aims to optimize a smooth nonconvex function $F$ (population risk) given only access to an approximation $f$ (empirical risk) that is pointwise close to","authors_text":"Chi Jin, Lydia T. Liu, Michael I. Jordan, Rong Ge","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T22:18:04Z","title":"On the Local Minima of the Empirical Risk"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09357","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":"sha256:7d36ac3d6e958e9a06fe0f023254be1cb060df8da9e0fca368d945235e187303","target":"record","created_at":"2026-05-18T00:02:55Z","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":"d9384ef8b7b2978e0dd297d8d2234b9786cdc1ae773f4f0e5e034959f538ab4f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-25T22:18:04Z","title_canon_sha256":"a32886221f076c46938a79ef71a80c947e0932158e8c08f1768986b8e0e621ea"},"schema_version":"1.0","source":{"id":"1803.09357","kind":"arxiv","version":2}},"canonical_sha256":"ef6239c5dfc84ad50e07b76c0287be4b61c008672fd20bd00fc999a5b7570411","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef6239c5dfc84ad50e07b76c0287be4b61c008672fd20bd00fc999a5b7570411","first_computed_at":"2026-05-18T00:02:55.009432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:55.009432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SvCaVBDMIBEcgdIfCDxnVkXFRDV/atIVkEihLbVURdAPCVwNwUFMfcNSuKD2rit44sy3ya4wQwi02VrrWdiYDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:55.010101Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09357","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d36ac3d6e958e9a06fe0f023254be1cb060df8da9e0fca368d945235e187303","sha256:2a29319f41dee93e5c18e66b8013b5d5839fb363b752215ddd901d3cdcf200c1"],"state_sha256":"5ac74c6d1f59f84ed6d732c6ed6f70b71cb2120758c89587fad55644cee9649d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SbZk2RSQj462AwQJNNHk6sCGLCSH8HBKdnYDfC6OeVsxT7gYbRfVJWtH8/nv6OrQMaHSP0TANMiX/7vFf81BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T10:35:27.959861Z","bundle_sha256":"1c8ae4384968455c85b6a590323d593c1042002316f1c1ddd935d54dbb1d51ed"}}