{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:Q6BIYYISASKCUXML3N6J4U4ZED","short_pith_number":"pith:Q6BIYYIS","canonical_record":{"source":{"id":"1705.07261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T05:09:33Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"bc043bb156412d622a5398686466ab5c892bf80ebdef96f8fa6938ba8f1c2b82","abstract_canon_sha256":"2f47ecb81c8ce00cb43dc77f82f33b192e2cf4f3f68443b548a7edfeb8be9af5"},"schema_version":"1.0"},"canonical_sha256":"87828c611204942a5d8bdb7c9e539920e8e8b3f26a570f943c178f70522fe298","source":{"kind":"arxiv","id":"1705.07261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07261","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07261v1","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07261","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"Q6BIYYISASKC","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q6BIYYISASKCUXML","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q6BIYYIS","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:Q6BIYYISASKCUXML3N6J4U4ZED","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T05:09:33Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"bc043bb156412d622a5398686466ab5c892bf80ebdef96f8fa6938ba8f1c2b82","abstract_canon_sha256":"2f47ecb81c8ce00cb43dc77f82f33b192e2cf4f3f68443b548a7edfeb8be9af5"},"schema_version":"1.0"},"canonical_sha256":"87828c611204942a5d8bdb7c9e539920e8e8b3f26a570f943c178f70522fe298","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:06.182765Z","signature_b64":"FpXjDuUr9kgNweZ+sF88dVzTyYtEEENljJPylPZdGnK60G/9Zok/X/SEtiBWhG5VL+W02dPLjZO+eAZrbCBsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87828c611204942a5d8bdb7c9e539920e8e8b3f26a570f943c178f70522fe298","last_reissued_at":"2026-05-18T00:44:06.182070Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:06.182070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07261","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":"2026-05-18T00:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jRG5Vi1eCII1X3sXDbDO4C4wFWgjo57Hv1+8MdC2MJRLGLH8Tole+08VF1rq6b6s70kJmxQhncyq/pJ0gJYODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:21:58.506378Z"},"content_sha256":"113813994470f5fa4f31a7d47db6cf480569cfd5b7b7b9c8bbd58e0a7554c669","schema_version":"1.0","event_id":"sha256:113813994470f5fa4f31a7d47db6cf480569cfd5b7b7b9c8bbd58e0a7554c669"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:Q6BIYYISASKCUXML3N6J4U4ZED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Recursive Gradient Algorithm for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Jie Liu, Katya Scheinberg, Lam M. Nguyen, Martin Tak\\'a\\v{c}","submitted_at":"2017-05-20T05:09:33Z","abstract_excerpt":"In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general nonconvex functions and a linear convergence rate for gradient dominated functions, both of which have some advantages compared to other modern stochastic gradient algorithms for nonconvex losses."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07261","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":"2026-05-18T00:44:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"emRGoUfPk+ugYDA1v8y4TSUZEX9VVcfjVwpFCUXbGUkrf/Bd36VaT2K58Df2Kz20kCYoqpLB9D6Dx41cQuTLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:21:58.507057Z"},"content_sha256":"5b618e8ebfafce2b0c62ff68d47d7a609757bc1225ef0af2a0468c4c8df4b661","schema_version":"1.0","event_id":"sha256:5b618e8ebfafce2b0c62ff68d47d7a609757bc1225ef0af2a0468c4c8df4b661"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6BIYYISASKCUXML3N6J4U4ZED/bundle.json","state_url":"https://pith.science/pith/Q6BIYYISASKCUXML3N6J4U4ZED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6BIYYISASKCUXML3N6J4U4ZED/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":"2026-05-26T17:21:58Z","links":{"resolver":"https://pith.science/pith/Q6BIYYISASKCUXML3N6J4U4ZED","bundle":"https://pith.science/pith/Q6BIYYISASKCUXML3N6J4U4ZED/bundle.json","state":"https://pith.science/pith/Q6BIYYISASKCUXML3N6J4U4ZED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6BIYYISASKCUXML3N6J4U4ZED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:Q6BIYYISASKCUXML3N6J4U4ZED","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":"2f47ecb81c8ce00cb43dc77f82f33b192e2cf4f3f68443b548a7edfeb8be9af5","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T05:09:33Z","title_canon_sha256":"bc043bb156412d622a5398686466ab5c892bf80ebdef96f8fa6938ba8f1c2b82"},"schema_version":"1.0","source":{"id":"1705.07261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07261","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07261v1","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07261","created_at":"2026-05-18T00:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"Q6BIYYISASKC","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"Q6BIYYISASKCUXML","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"Q6BIYYIS","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:5b618e8ebfafce2b0c62ff68d47d7a609757bc1225ef0af2a0468c4c8df4b661","target":"graph","created_at":"2026-05-18T00:44:06Z","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":"In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general nonconvex functions and a linear convergence rate for gradient dominated functions, both of which have some advantages compared to other modern stochastic gradient algorithms for nonconvex losses.","authors_text":"Jie Liu, Katya Scheinberg, Lam M. Nguyen, Martin Tak\\'a\\v{c}","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T05:09:33Z","title":"Stochastic Recursive Gradient Algorithm for Nonconvex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07261","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":"sha256:113813994470f5fa4f31a7d47db6cf480569cfd5b7b7b9c8bbd58e0a7554c669","target":"record","created_at":"2026-05-18T00:44:06Z","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":"2f47ecb81c8ce00cb43dc77f82f33b192e2cf4f3f68443b548a7edfeb8be9af5","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-20T05:09:33Z","title_canon_sha256":"bc043bb156412d622a5398686466ab5c892bf80ebdef96f8fa6938ba8f1c2b82"},"schema_version":"1.0","source":{"id":"1705.07261","kind":"arxiv","version":1}},"canonical_sha256":"87828c611204942a5d8bdb7c9e539920e8e8b3f26a570f943c178f70522fe298","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87828c611204942a5d8bdb7c9e539920e8e8b3f26a570f943c178f70522fe298","first_computed_at":"2026-05-18T00:44:06.182070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:06.182070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FpXjDuUr9kgNweZ+sF88dVzTyYtEEENljJPylPZdGnK60G/9Zok/X/SEtiBWhG5VL+W02dPLjZO+eAZrbCBsBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:06.182765Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:113813994470f5fa4f31a7d47db6cf480569cfd5b7b7b9c8bbd58e0a7554c669","sha256:5b618e8ebfafce2b0c62ff68d47d7a609757bc1225ef0af2a0468c4c8df4b661"],"state_sha256":"57b1767e2f359013b508eaaf5f0c6b05aa5ece106b739cc85fef5aca56d55563"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kyfs+OW1UXfyB5wbR4PACuVmAjPnDHiFBmmhdP8sheHho+Oyi96rj349ryfl3w97kTdN8vd1D3Svb9VtFEDhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:21:58.510790Z","bundle_sha256":"2471b255a823541a02bbb614ab3127f34ffdf0b4efd591de8ff0b9674f6afcb2"}}