{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HBBFO5HD2NQOQLSPHRLXBE7NI6","short_pith_number":"pith:HBBFO5HD","canonical_record":{"source":{"id":"1901.08369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-24T11:56:59Z","cross_cats_sorted":[],"title_canon_sha256":"832eeb037e8b59b93e436ae00c2579703f7d816e80c6703b0194336d2b9710bb","abstract_canon_sha256":"fc602aeadbf885e64c8e860af10fc40fc1907095823863ae48ce4ef376070895"},"schema_version":"1.0"},"canonical_sha256":"38425774e3d360e82e4f3c577093ed47b6b7af77aada1d5f6bdcef59ab390eac","source":{"kind":"arxiv","id":"1901.08369","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08369","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08369v2","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08369","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"pith_short_12","alias_value":"HBBFO5HD2NQO","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HBBFO5HD2NQOQLSP","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HBBFO5HD","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HBBFO5HD2NQOQLSPHRLXBE7NI6","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-24T11:56:59Z","cross_cats_sorted":[],"title_canon_sha256":"832eeb037e8b59b93e436ae00c2579703f7d816e80c6703b0194336d2b9710bb","abstract_canon_sha256":"fc602aeadbf885e64c8e860af10fc40fc1907095823863ae48ce4ef376070895"},"schema_version":"1.0"},"canonical_sha256":"38425774e3d360e82e4f3c577093ed47b6b7af77aada1d5f6bdcef59ab390eac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:18.766807Z","signature_b64":"QLX7PnzbYpwPMsQ6+lxkFJAEmwPWjWnWCRt/Anw8mUoPxLSizA8dK300c7FiAhhC+bD3+6J3FDHTn3Oc/oBIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38425774e3d360e82e4f3c577093ed47b6b7af77aada1d5f6bdcef59ab390eac","last_reissued_at":"2026-05-17T23:46:18.766078Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:18.766078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08369","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":"2026-05-17T23:46:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7pkLZT3B7x3UN6y/+kxaBMZnsx/9803CyPVMAz8nYPOU0uO2ViEendyeSF8G86bdTGj56koPePrPKVbJ3EaPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T09:22:07.576254Z"},"content_sha256":"6643eb4a8451a4ecc4ef77e8458a23a01fa997561b3d15abff7b33a4ad745005","schema_version":"1.0","event_id":"sha256:6643eb4a8451a4ecc4ef77e8458a23a01fa997561b3d15abff7b33a4ad745005"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HBBFO5HD2NQOQLSPHRLXBE7NI6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Akiko Takeda, Michael R. Metel","submitted_at":"2019-01-24T11:56:59Z","abstract_excerpt":"Our work focuses on stochastic gradient methods for optimizing a smooth non-convex loss function with a non-smooth non-convex regularizer. Research on this class of problem is quite limited, and until recently no non-asymptotic convergence results have been reported. We present two simple stochastic gradient algorithms, for finite-sum and general stochastic optimization problems, which have superior convergence complexities compared to the current state-of-the-art. We also compare our algorithms' performance in practice for empirical risk minimization."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08369","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":"2026-05-17T23:46:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYDCwBhwTEA9BZEKtTKd8fQ1Sok47c0YSFg2/bCllrXLq5yG0yJZ/0E3Te1IyJ8cPeU58ydM8wS1XlOi0P9TCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T09:22:07.576632Z"},"content_sha256":"e264f4d2d09c98d3c6fa48ce30cfbbd525d7ab176fb325b4fd4856ed1550ddc8","schema_version":"1.0","event_id":"sha256:e264f4d2d09c98d3c6fa48ce30cfbbd525d7ab176fb325b4fd4856ed1550ddc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HBBFO5HD2NQOQLSPHRLXBE7NI6/bundle.json","state_url":"https://pith.science/pith/HBBFO5HD2NQOQLSPHRLXBE7NI6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HBBFO5HD2NQOQLSPHRLXBE7NI6/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":"2026-06-25T09:22:07Z","links":{"resolver":"https://pith.science/pith/HBBFO5HD2NQOQLSPHRLXBE7NI6","bundle":"https://pith.science/pith/HBBFO5HD2NQOQLSPHRLXBE7NI6/bundle.json","state":"https://pith.science/pith/HBBFO5HD2NQOQLSPHRLXBE7NI6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HBBFO5HD2NQOQLSPHRLXBE7NI6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HBBFO5HD2NQOQLSPHRLXBE7NI6","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":"fc602aeadbf885e64c8e860af10fc40fc1907095823863ae48ce4ef376070895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-24T11:56:59Z","title_canon_sha256":"832eeb037e8b59b93e436ae00c2579703f7d816e80c6703b0194336d2b9710bb"},"schema_version":"1.0","source":{"id":"1901.08369","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08369","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08369v2","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08369","created_at":"2026-05-17T23:46:18Z"},{"alias_kind":"pith_short_12","alias_value":"HBBFO5HD2NQO","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HBBFO5HD2NQOQLSP","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HBBFO5HD","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:e264f4d2d09c98d3c6fa48ce30cfbbd525d7ab176fb325b4fd4856ed1550ddc8","target":"graph","created_at":"2026-05-17T23:46:18Z","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":"Our work focuses on stochastic gradient methods for optimizing a smooth non-convex loss function with a non-smooth non-convex regularizer. Research on this class of problem is quite limited, and until recently no non-asymptotic convergence results have been reported. We present two simple stochastic gradient algorithms, for finite-sum and general stochastic optimization problems, which have superior convergence complexities compared to the current state-of-the-art. We also compare our algorithms' performance in practice for empirical risk minimization.","authors_text":"Akiko Takeda, Michael R. Metel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-24T11:56:59Z","title":"Simple Stochastic Gradient Methods for Non-Smooth Non-Convex Regularized Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08369","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":"sha256:6643eb4a8451a4ecc4ef77e8458a23a01fa997561b3d15abff7b33a4ad745005","target":"record","created_at":"2026-05-17T23:46:18Z","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":"fc602aeadbf885e64c8e860af10fc40fc1907095823863ae48ce4ef376070895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-01-24T11:56:59Z","title_canon_sha256":"832eeb037e8b59b93e436ae00c2579703f7d816e80c6703b0194336d2b9710bb"},"schema_version":"1.0","source":{"id":"1901.08369","kind":"arxiv","version":2}},"canonical_sha256":"38425774e3d360e82e4f3c577093ed47b6b7af77aada1d5f6bdcef59ab390eac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38425774e3d360e82e4f3c577093ed47b6b7af77aada1d5f6bdcef59ab390eac","first_computed_at":"2026-05-17T23:46:18.766078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:18.766078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QLX7PnzbYpwPMsQ6+lxkFJAEmwPWjWnWCRt/Anw8mUoPxLSizA8dK300c7FiAhhC+bD3+6J3FDHTn3Oc/oBIAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:18.766807Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08369","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6643eb4a8451a4ecc4ef77e8458a23a01fa997561b3d15abff7b33a4ad745005","sha256:e264f4d2d09c98d3c6fa48ce30cfbbd525d7ab176fb325b4fd4856ed1550ddc8"],"state_sha256":"1fd743fa92790aaf7faa11d04ad4695ff11614bc6dc169a127f740b35d872fe2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQo/eEfA4Vr2bpFbCpGm22aNm1W7QpJ3d34wFnzZCmqbt1OvhTxJHBTUvLNkt2SdEUE1HTBO80fC5Kdo96d0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T09:22:07.578557Z","bundle_sha256":"b0b3762481e4720482f506d0c354b5d24958a91a8e9668f2d49b5c2349550411"}}