{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:Q3EUQOSBFHDB43CZNIDWWLNLAJ","short_pith_number":"pith:Q3EUQOSB","canonical_record":{"source":{"id":"1307.3176","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-11T16:36:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"52a24a8fbdf38ecf55a000ceee78708dd9b6e39094d911da810dcacab6e2e9fc","abstract_canon_sha256":"18c33d6cbb8bef2bbd9e85ef7ce5e99968b85e3cea06c17976b61aaee3ea484d"},"schema_version":"1.0"},"canonical_sha256":"86c9483a4129c61e6c596a076b2dab0267f3b467b24e3851e702591fc62c7c50","source":{"kind":"arxiv","id":"1307.3176","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1307.3176","created_at":"2026-05-18T02:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"1307.3176v4","created_at":"2026-05-18T02:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.3176","created_at":"2026-05-18T02:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q3EUQOSBFHDB","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q3EUQOSBFHDB43CZ","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q3EUQOSB","created_at":"2026-05-18T12:27:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:Q3EUQOSBFHDB43CZNIDWWLNLAJ","target":"record","payload":{"canonical_record":{"source":{"id":"1307.3176","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-11T16:36:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"52a24a8fbdf38ecf55a000ceee78708dd9b6e39094d911da810dcacab6e2e9fc","abstract_canon_sha256":"18c33d6cbb8bef2bbd9e85ef7ce5e99968b85e3cea06c17976b61aaee3ea484d"},"schema_version":"1.0"},"canonical_sha256":"86c9483a4129c61e6c596a076b2dab0267f3b467b24e3851e702591fc62c7c50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:33:25.635620Z","signature_b64":"bQ3l+2yX1f2tkBrfpr+///e45//QzMbvPWzza0Dj9s54d4FIwjTwoCsNrdtOF2kSjOyqW1ETI9D0UdtWuo2xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c9483a4129c61e6c596a076b2dab0267f3b467b24e3851e702591fc62c7c50","last_reissued_at":"2026-05-18T02:33:25.634935Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:33:25.634935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1307.3176","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:33:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFXZuhCzTUivz7m/tJ2h/7Z5I7BtwCK9SYWcCIf9ZI0LQYR8ljfIw+tHvF/X6bhsEkOJFoLppB3FZv9vhctICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:14:44.638244Z"},"content_sha256":"bef4dcde4cc74a2a2e9ea03d05fc9de91801809811cef99276f440679b59725d","schema_version":"1.0","event_id":"sha256:bef4dcde4cc74a2a2e9ea03d05fc9de91801809811cef99276f440679b59725d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:Q3EUQOSBFHDB43CZNIDWWLNLAJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast gradient descent for drifting least squares regression, with application to bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nathaniel Korda, Prashanth L.A., R\\'emi Munos","submitted_at":"2013-07-11T16:36:29Z","abstract_excerpt":"Online learning algorithms require to often recompute least squares regression estimates of parameters. We study improving the computational complexity of such algorithms by using stochastic gradient descent (SGD) type schemes in place of classic regression solvers. We show that SGD schemes efficiently track the true solutions of the regression problems, even in the presence of a drift. This finding coupled with an $O(d)$ improvement in complexity, where $d$ is the dimension of the data, make them attractive for implementation in the big data settings. In the case when strong convexity in the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.3176","kind":"arxiv","version":4},"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":"2026-05-18T02:33:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9+Wf063pXiTducDxCQtgAhgoH1SCFJc4Qty0n6KLHOWs0y6s85sVc8J8FEJxDCWy+vcbdKYBxoEanj/hdS/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:14:44.638976Z"},"content_sha256":"c45ac64096eff3dd7d99f0bf78e1ba535bea11392acc59352f34ffe5cba112a1","schema_version":"1.0","event_id":"sha256:c45ac64096eff3dd7d99f0bf78e1ba535bea11392acc59352f34ffe5cba112a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3EUQOSBFHDB43CZNIDWWLNLAJ/bundle.json","state_url":"https://pith.science/pith/Q3EUQOSBFHDB43CZNIDWWLNLAJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3EUQOSBFHDB43CZNIDWWLNLAJ/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":"2026-05-31T07:14:44Z","links":{"resolver":"https://pith.science/pith/Q3EUQOSBFHDB43CZNIDWWLNLAJ","bundle":"https://pith.science/pith/Q3EUQOSBFHDB43CZNIDWWLNLAJ/bundle.json","state":"https://pith.science/pith/Q3EUQOSBFHDB43CZNIDWWLNLAJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3EUQOSBFHDB43CZNIDWWLNLAJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:Q3EUQOSBFHDB43CZNIDWWLNLAJ","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":"18c33d6cbb8bef2bbd9e85ef7ce5e99968b85e3cea06c17976b61aaee3ea484d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-11T16:36:29Z","title_canon_sha256":"52a24a8fbdf38ecf55a000ceee78708dd9b6e39094d911da810dcacab6e2e9fc"},"schema_version":"1.0","source":{"id":"1307.3176","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1307.3176","created_at":"2026-05-18T02:33:25Z"},{"alias_kind":"arxiv_version","alias_value":"1307.3176v4","created_at":"2026-05-18T02:33:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.3176","created_at":"2026-05-18T02:33:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q3EUQOSBFHDB","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q3EUQOSBFHDB43CZ","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q3EUQOSB","created_at":"2026-05-18T12:27:57Z"}],"graph_snapshots":[{"event_id":"sha256:c45ac64096eff3dd7d99f0bf78e1ba535bea11392acc59352f34ffe5cba112a1","target":"graph","created_at":"2026-05-18T02:33:25Z","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":"Online learning algorithms require to often recompute least squares regression estimates of parameters. We study improving the computational complexity of such algorithms by using stochastic gradient descent (SGD) type schemes in place of classic regression solvers. We show that SGD schemes efficiently track the true solutions of the regression problems, even in the presence of a drift. This finding coupled with an $O(d)$ improvement in complexity, where $d$ is the dimension of the data, make them attractive for implementation in the big data settings. In the case when strong convexity in the ","authors_text":"Nathaniel Korda, Prashanth L.A., R\\'emi Munos","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-11T16:36:29Z","title":"Fast gradient descent for drifting least squares regression, with application to bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.3176","kind":"arxiv","version":4},"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:bef4dcde4cc74a2a2e9ea03d05fc9de91801809811cef99276f440679b59725d","target":"record","created_at":"2026-05-18T02:33:25Z","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":"18c33d6cbb8bef2bbd9e85ef7ce5e99968b85e3cea06c17976b61aaee3ea484d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-07-11T16:36:29Z","title_canon_sha256":"52a24a8fbdf38ecf55a000ceee78708dd9b6e39094d911da810dcacab6e2e9fc"},"schema_version":"1.0","source":{"id":"1307.3176","kind":"arxiv","version":4}},"canonical_sha256":"86c9483a4129c61e6c596a076b2dab0267f3b467b24e3851e702591fc62c7c50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86c9483a4129c61e6c596a076b2dab0267f3b467b24e3851e702591fc62c7c50","first_computed_at":"2026-05-18T02:33:25.634935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:33:25.634935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQ3l+2yX1f2tkBrfpr+///e45//QzMbvPWzza0Dj9s54d4FIwjTwoCsNrdtOF2kSjOyqW1ETI9D0UdtWuo2xBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:33:25.635620Z","signed_message":"canonical_sha256_bytes"},"source_id":"1307.3176","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bef4dcde4cc74a2a2e9ea03d05fc9de91801809811cef99276f440679b59725d","sha256:c45ac64096eff3dd7d99f0bf78e1ba535bea11392acc59352f34ffe5cba112a1"],"state_sha256":"11ebc204aa71780a23ae0f1f431fa3d616a70082e71501c894c90f066b1034d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WFXNYq5s0meshqHvN2+mKhMz96t4G7EOIi7XzD2CUevZwrgx1ZAgC+ZWKa8XairttmVrs22zT8qCueuIMXUqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:14:44.643566Z","bundle_sha256":"2aa306a0f9ddcd2f6e4ca36539ecd91a02c365dc8ad79a551c9ceb5bdeac2cc8"}}