{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:YKLEH2K4MGKUFSACTRKV76DXBL","short_pith_number":"pith:YKLEH2K4","canonical_record":{"source":{"id":"1603.02412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-03-08T08:26:28Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0a5ba2ac54b3a2f1c0d40812fc9676e5b5499463693dc80da729520703ee84f9","abstract_canon_sha256":"4810e2a10bf358e201730ed8dbc94d9de738e2e324bcc9069088244d178cb40e"},"schema_version":"1.0"},"canonical_sha256":"c29643e95c619542c8029c555ff8770adcbe02c09a2d069e12a172e0d9ad607f","source":{"kind":"arxiv","id":"1603.02412","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.02412","created_at":"2026-05-18T01:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"1603.02412v1","created_at":"2026-05-18T01:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02412","created_at":"2026-05-18T01:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"YKLEH2K4MGKU","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YKLEH2K4MGKUFSAC","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YKLEH2K4","created_at":"2026-05-18T12:30:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:YKLEH2K4MGKUFSACTRKV76DXBL","target":"record","payload":{"canonical_record":{"source":{"id":"1603.02412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-03-08T08:26:28Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"0a5ba2ac54b3a2f1c0d40812fc9676e5b5499463693dc80da729520703ee84f9","abstract_canon_sha256":"4810e2a10bf358e201730ed8dbc94d9de738e2e324bcc9069088244d178cb40e"},"schema_version":"1.0"},"canonical_sha256":"c29643e95c619542c8029c555ff8770adcbe02c09a2d069e12a172e0d9ad607f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:23.425838Z","signature_b64":"8Arxc8htOt/XsBC2d4sqleJ8Mt6MlVnXUNUYMggoF4+fmC27bvwbYy69QLZpi3IDaBLxolFNuex5nuvWHdQdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c29643e95c619542c8029c555ff8770adcbe02c09a2d069e12a172e0d9ad607f","last_reissued_at":"2026-05-18T01:19:23.425155Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:23.425155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.02412","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":"2026-05-18T01:19:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dXQNLOY166fAPa0Sj+5Y7ygDSy6Ak13hh+5VRvLeyQLn1iz8LTX8iCg8Gzy4yM9zeKMHQYPwPMs69jKNQHq8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:46:35.061251Z"},"content_sha256":"aa3636d32fd8b99d40f53f1a74608e5562469f6c17e0e6d249a94cba805e6708","schema_version":"1.0","event_id":"sha256:aa3636d32fd8b99d40f53f1a74608e5562469f6c17e0e6d249a94cba805e6708"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:YKLEH2K4MGKUFSACTRKV76DXBL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic dual averaging methods using variance reduction techniques for regularized empirical risk minimization problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Taiji Suzuki, Tomoya Murata","submitted_at":"2016-03-08T08:26:28Z","abstract_excerpt":"We consider a composite convex minimization problem associated with regularized empirical risk minimization, which often arises in machine learning. We propose two new stochastic gradient methods that are based on stochastic dual averaging method with variance reduction. Our methods generate a sparser solution than the existing methods because we do not need to take the average of the history of the solutions. This is favorable in terms of both interpretability and generalization. Moreover, our methods have theoretical support for both a strongly and a non-strongly convex regularizer and achie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02412","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":"2026-05-18T01:19:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b1xcVB144zQ+o3L5CA1Yoxp1A8nByaLBYZHJ/icGtM+wHdMAg0HcL9C5fY+AmR6EJmUXimuq1sNSPpHQ+2iKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:46:35.061613Z"},"content_sha256":"aa18f918e773ac8794525d5b902d412202380675ab2edd1d62e61b485570fdb5","schema_version":"1.0","event_id":"sha256:aa18f918e773ac8794525d5b902d412202380675ab2edd1d62e61b485570fdb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YKLEH2K4MGKUFSACTRKV76DXBL/bundle.json","state_url":"https://pith.science/pith/YKLEH2K4MGKUFSACTRKV76DXBL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YKLEH2K4MGKUFSACTRKV76DXBL/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":"2026-06-27T23:46:35Z","links":{"resolver":"https://pith.science/pith/YKLEH2K4MGKUFSACTRKV76DXBL","bundle":"https://pith.science/pith/YKLEH2K4MGKUFSACTRKV76DXBL/bundle.json","state":"https://pith.science/pith/YKLEH2K4MGKUFSACTRKV76DXBL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YKLEH2K4MGKUFSACTRKV76DXBL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:YKLEH2K4MGKUFSACTRKV76DXBL","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":"4810e2a10bf358e201730ed8dbc94d9de738e2e324bcc9069088244d178cb40e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-03-08T08:26:28Z","title_canon_sha256":"0a5ba2ac54b3a2f1c0d40812fc9676e5b5499463693dc80da729520703ee84f9"},"schema_version":"1.0","source":{"id":"1603.02412","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.02412","created_at":"2026-05-18T01:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"1603.02412v1","created_at":"2026-05-18T01:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.02412","created_at":"2026-05-18T01:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"YKLEH2K4MGKU","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_16","alias_value":"YKLEH2K4MGKUFSAC","created_at":"2026-05-18T12:30:53Z"},{"alias_kind":"pith_short_8","alias_value":"YKLEH2K4","created_at":"2026-05-18T12:30:53Z"}],"graph_snapshots":[{"event_id":"sha256:aa18f918e773ac8794525d5b902d412202380675ab2edd1d62e61b485570fdb5","target":"graph","created_at":"2026-05-18T01:19:23Z","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":"We consider a composite convex minimization problem associated with regularized empirical risk minimization, which often arises in machine learning. We propose two new stochastic gradient methods that are based on stochastic dual averaging method with variance reduction. Our methods generate a sparser solution than the existing methods because we do not need to take the average of the history of the solutions. This is favorable in terms of both interpretability and generalization. Moreover, our methods have theoretical support for both a strongly and a non-strongly convex regularizer and achie","authors_text":"Taiji Suzuki, Tomoya Murata","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-03-08T08:26:28Z","title":"Stochastic dual averaging methods using variance reduction techniques for regularized empirical risk minimization problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.02412","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:aa3636d32fd8b99d40f53f1a74608e5562469f6c17e0e6d249a94cba805e6708","target":"record","created_at":"2026-05-18T01:19:23Z","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":"4810e2a10bf358e201730ed8dbc94d9de738e2e324bcc9069088244d178cb40e","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-03-08T08:26:28Z","title_canon_sha256":"0a5ba2ac54b3a2f1c0d40812fc9676e5b5499463693dc80da729520703ee84f9"},"schema_version":"1.0","source":{"id":"1603.02412","kind":"arxiv","version":1}},"canonical_sha256":"c29643e95c619542c8029c555ff8770adcbe02c09a2d069e12a172e0d9ad607f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c29643e95c619542c8029c555ff8770adcbe02c09a2d069e12a172e0d9ad607f","first_computed_at":"2026-05-18T01:19:23.425155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:23.425155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Arxc8htOt/XsBC2d4sqleJ8Mt6MlVnXUNUYMggoF4+fmC27bvwbYy69QLZpi3IDaBLxolFNuex5nuvWHdQdAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:23.425838Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.02412","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa3636d32fd8b99d40f53f1a74608e5562469f6c17e0e6d249a94cba805e6708","sha256:aa18f918e773ac8794525d5b902d412202380675ab2edd1d62e61b485570fdb5"],"state_sha256":"3b76210c2cab7cd1752066c5e631cff2958f073ca18ad4829296599a6bb820df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YO63d6IsNshISk1RgwjCL2DA2adjxfrJtegDM/imY8n2HmePtWVpxW+i20L5anI2QqjHmvPTQo3gf9kUGOxkDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T23:46:35.063984Z","bundle_sha256":"777fa73ce355776433561aa5c3d2cb239d4ccff129609fa9a41e37f2df83811b"}}