{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:57VYFLHYECI5VUEF5WDFF3QZSZ","short_pith_number":"pith:57VYFLHY","canonical_record":{"source":{"id":"1704.08227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-26T17:30:27Z","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"title_canon_sha256":"d5664cc86486d91009b63793d90e2a452221ef1e4c0fc108a969c836c160fc3e","abstract_canon_sha256":"b47f0fcdffaf1fc5ef308bdb30abf2c0e484d28e1dac8f3d6c4f53aa1c1545bb"},"schema_version":"1.0"},"canonical_sha256":"efeb82acf82091dad085ed8652ee199659adccb3d59067d6b525bfcb10a67694","source":{"kind":"arxiv","id":"1704.08227","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08227","created_at":"2026-05-18T00:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08227v2","created_at":"2026-05-18T00:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08227","created_at":"2026-05-18T00:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"57VYFLHYECI5","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"57VYFLHYECI5VUEF","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"57VYFLHY","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:57VYFLHYECI5VUEF5WDFF3QZSZ","target":"record","payload":{"canonical_record":{"source":{"id":"1704.08227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-26T17:30:27Z","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"title_canon_sha256":"d5664cc86486d91009b63793d90e2a452221ef1e4c0fc108a969c836c160fc3e","abstract_canon_sha256":"b47f0fcdffaf1fc5ef308bdb30abf2c0e484d28e1dac8f3d6c4f53aa1c1545bb"},"schema_version":"1.0"},"canonical_sha256":"efeb82acf82091dad085ed8652ee199659adccb3d59067d6b525bfcb10a67694","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:10.090393Z","signature_b64":"zYdm6rD2U+PjPY5OlXYK24E7IpPBM7+5yuvewrKUhUZb4gWNzuIfzm9tUYr1+hvUbtl+wPu8cXJ4sB8qq2B/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efeb82acf82091dad085ed8652ee199659adccb3d59067d6b525bfcb10a67694","last_reissued_at":"2026-05-18T00:09:10.089609Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:10.089609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.08227","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":"2026-05-18T00:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQlQIkIVkAbXd4u9CZc0A2C28inaNbcf0KftY0xAOr9ymV27xkFTk8EsmCs2fdOYc+Z71gArvZbOXUEiKYdmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:37:30.592859Z"},"content_sha256":"d4f87ccec21d130deb1ab1ad546c219a78a96466ad21d219d4709b68e95ba3fe","schema_version":"1.0","event_id":"sha256:d4f87ccec21d130deb1ab1ad546c219a78a96466ad21d219d4709b68e95ba3fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:57VYFLHYECI5VUEF5WDFF3QZSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Stochastic Gradient Descent For Least Squares Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Aaron Sidford, Praneeth Netrapalli, Prateek Jain, Rahul Kidambi, Sham M. Kakade","submitted_at":"2017-04-26T17:30:27Z","abstract_excerpt":"There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e.g. Nesterov's acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their instability and error accumulation, a notion made precise in d'Aspremont 2008 and Devolder, Glineur, and Nesterov 2014. This work considers these issues for the special case of stochastic approximation for the least squares regression problem, and our main result refutes the conventional wisdom by showing that acceleration can be made robust to statistical errors. In particular,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08227","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":"2026-05-18T00:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CPf34GUJ9bmP50gBvEreTQuM/r0wxFvYRA03+Wp3rGssaINbarvF6kpMMVt57kX4u8AJlqqvNxvQdFeho+MCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:37:30.593795Z"},"content_sha256":"122b4ff21c462bf0b8c365c0aaf8234169d818dae8c916fece81a07cde5366cc","schema_version":"1.0","event_id":"sha256:122b4ff21c462bf0b8c365c0aaf8234169d818dae8c916fece81a07cde5366cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57VYFLHYECI5VUEF5WDFF3QZSZ/bundle.json","state_url":"https://pith.science/pith/57VYFLHYECI5VUEF5WDFF3QZSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57VYFLHYECI5VUEF5WDFF3QZSZ/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":"2026-05-25T19:37:30Z","links":{"resolver":"https://pith.science/pith/57VYFLHYECI5VUEF5WDFF3QZSZ","bundle":"https://pith.science/pith/57VYFLHYECI5VUEF5WDFF3QZSZ/bundle.json","state":"https://pith.science/pith/57VYFLHYECI5VUEF5WDFF3QZSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57VYFLHYECI5VUEF5WDFF3QZSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:57VYFLHYECI5VUEF5WDFF3QZSZ","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":"b47f0fcdffaf1fc5ef308bdb30abf2c0e484d28e1dac8f3d6c4f53aa1c1545bb","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-26T17:30:27Z","title_canon_sha256":"d5664cc86486d91009b63793d90e2a452221ef1e4c0fc108a969c836c160fc3e"},"schema_version":"1.0","source":{"id":"1704.08227","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08227","created_at":"2026-05-18T00:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08227v2","created_at":"2026-05-18T00:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08227","created_at":"2026-05-18T00:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"57VYFLHYECI5","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"57VYFLHYECI5VUEF","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"57VYFLHY","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:122b4ff21c462bf0b8c365c0aaf8234169d818dae8c916fece81a07cde5366cc","target":"graph","created_at":"2026-05-18T00:09:10Z","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":"There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e.g. Nesterov's acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their instability and error accumulation, a notion made precise in d'Aspremont 2008 and Devolder, Glineur, and Nesterov 2014. This work considers these issues for the special case of stochastic approximation for the least squares regression problem, and our main result refutes the conventional wisdom by showing that acceleration can be made robust to statistical errors. In particular,","authors_text":"Aaron Sidford, Praneeth Netrapalli, Prateek Jain, Rahul Kidambi, Sham M. Kakade","cross_cats":["cs.LG","math.OC","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-26T17:30:27Z","title":"Accelerating Stochastic Gradient Descent For Least Squares Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08227","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:d4f87ccec21d130deb1ab1ad546c219a78a96466ad21d219d4709b68e95ba3fe","target":"record","created_at":"2026-05-18T00:09:10Z","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":"b47f0fcdffaf1fc5ef308bdb30abf2c0e484d28e1dac8f3d6c4f53aa1c1545bb","cross_cats_sorted":["cs.LG","math.OC","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-26T17:30:27Z","title_canon_sha256":"d5664cc86486d91009b63793d90e2a452221ef1e4c0fc108a969c836c160fc3e"},"schema_version":"1.0","source":{"id":"1704.08227","kind":"arxiv","version":2}},"canonical_sha256":"efeb82acf82091dad085ed8652ee199659adccb3d59067d6b525bfcb10a67694","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efeb82acf82091dad085ed8652ee199659adccb3d59067d6b525bfcb10a67694","first_computed_at":"2026-05-18T00:09:10.089609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:10.089609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zYdm6rD2U+PjPY5OlXYK24E7IpPBM7+5yuvewrKUhUZb4gWNzuIfzm9tUYr1+hvUbtl+wPu8cXJ4sB8qq2B/CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:10.090393Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.08227","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4f87ccec21d130deb1ab1ad546c219a78a96466ad21d219d4709b68e95ba3fe","sha256:122b4ff21c462bf0b8c365c0aaf8234169d818dae8c916fece81a07cde5366cc"],"state_sha256":"f49f02499b8ba9cc739a0f1997e45ab2ac654b3576af5541d4bd990df85cde44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6W9/ySFWfnw6Hf59oc4Y9enxEOMvHrl08kQpUEmIiNx3eb5JjC6XTISF52wgV4BIoV10qk1+CS8lM41vgx+oDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:37:30.597715Z","bundle_sha256":"01f0b05e5d5580073a62a9eb973df4eeb708043f443beecdb42bde6a7661bb8f"}}