{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:WHG7IVE4UINBPS4HYRIJS46VUF","short_pith_number":"pith:WHG7IVE4","canonical_record":{"source":{"id":"1408.0361","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-08-02T11:22:52Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"9db757ed5a1be373eda1241a295e622dbf5b839a2db0deeb271874c9c8cda868","abstract_canon_sha256":"a128419a6388a197b4a6d4461a4eea295587f47894eccdbe17ddc26574fd4020"},"schema_version":"1.0"},"canonical_sha256":"b1cdf4549ca21a17cb87c4509973d5a155368971a38e9ac0e3ce46b6ef33687a","source":{"kind":"arxiv","id":"1408.0361","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.0361","created_at":"2026-05-18T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"1408.0361v3","created_at":"2026-05-18T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.0361","created_at":"2026-05-18T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"WHG7IVE4UINB","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WHG7IVE4UINBPS4H","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WHG7IVE4","created_at":"2026-05-18T12:28:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:WHG7IVE4UINBPS4HYRIJS46VUF","target":"record","payload":{"canonical_record":{"source":{"id":"1408.0361","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-08-02T11:22:52Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"9db757ed5a1be373eda1241a295e622dbf5b839a2db0deeb271874c9c8cda868","abstract_canon_sha256":"a128419a6388a197b4a6d4461a4eea295587f47894eccdbe17ddc26574fd4020"},"schema_version":"1.0"},"canonical_sha256":"b1cdf4549ca21a17cb87c4509973d5a155368971a38e9ac0e3ce46b6ef33687a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:10.308254Z","signature_b64":"Gqa7xRSEenX9zJon8cdOa5qYRG21qH4TBAqJ0S6WhGKrtfeRe14e6M6jJ/6RRL5zEDY7+Rea1TeqIo/VLRa3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1cdf4549ca21a17cb87c4509973d5a155368971a38e9ac0e3ce46b6ef33687a","last_reissued_at":"2026-05-18T01:18:10.307588Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:10.307588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1408.0361","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uAt7afO6MHgqwXLuE3CLUj6fT6qRv7jH3srMqL16l4T68s3Srh4WDceoxl8iyp/x0FnfHC8/Ow6YBwD9awE/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:20:18.937763Z"},"content_sha256":"e9ccced3eb912fe06ecd68187fd08933e131d39096538f7dab7093f9c870f9ff","schema_version":"1.0","event_id":"sha256:e9ccced3eb912fe06ecd68187fd08933e131d39096538f7dab7093f9c870f9ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:WHG7IVE4UINBPS4HYRIJS46VUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-parametric Stochastic Approximation with Large Step sizes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Aymeric Dieuleveut, Francis Bach","submitted_at":"2014-08-02T11:22:52Z","abstract_excerpt":"We consider the random-design least-squares regression problem within the reproducing kernel Hilbert space (RKHS) framework. Given a stream of independent and identically distributed input/output data, we aim to learn a regression function within an RKHS $\\mathcal{H}$, even if the optimal predictor (i.e., the conditional expectation) is not in $\\mathcal{H}$. In a stochastic approximation framework where the estimator is updated after each observation, we show that the averaged unregularized least-mean-square algorithm (a form of stochastic gradient), given a sufficient large step-size, attains"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.0361","kind":"arxiv","version":3},"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":"2026-05-18T01:18:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7PWTQ5XogK7GXB/qDwBsV2czSsdw0ZZKJVF4MV1wbiNE+w0V5cYsyYRI1OkuM1vPtfIAjOb9t9m72crkD388Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:20:18.938398Z"},"content_sha256":"7ff9add60e182fb327940dfb2eedf0a9549eb802be7d08241b4c641d7266eb64","schema_version":"1.0","event_id":"sha256:7ff9add60e182fb327940dfb2eedf0a9549eb802be7d08241b4c641d7266eb64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WHG7IVE4UINBPS4HYRIJS46VUF/bundle.json","state_url":"https://pith.science/pith/WHG7IVE4UINBPS4HYRIJS46VUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WHG7IVE4UINBPS4HYRIJS46VUF/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":"2026-05-29T18:20:18Z","links":{"resolver":"https://pith.science/pith/WHG7IVE4UINBPS4HYRIJS46VUF","bundle":"https://pith.science/pith/WHG7IVE4UINBPS4HYRIJS46VUF/bundle.json","state":"https://pith.science/pith/WHG7IVE4UINBPS4HYRIJS46VUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WHG7IVE4UINBPS4HYRIJS46VUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:WHG7IVE4UINBPS4HYRIJS46VUF","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":"a128419a6388a197b4a6d4461a4eea295587f47894eccdbe17ddc26574fd4020","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-08-02T11:22:52Z","title_canon_sha256":"9db757ed5a1be373eda1241a295e622dbf5b839a2db0deeb271874c9c8cda868"},"schema_version":"1.0","source":{"id":"1408.0361","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.0361","created_at":"2026-05-18T01:18:10Z"},{"alias_kind":"arxiv_version","alias_value":"1408.0361v3","created_at":"2026-05-18T01:18:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.0361","created_at":"2026-05-18T01:18:10Z"},{"alias_kind":"pith_short_12","alias_value":"WHG7IVE4UINB","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"WHG7IVE4UINBPS4H","created_at":"2026-05-18T12:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"WHG7IVE4","created_at":"2026-05-18T12:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:7ff9add60e182fb327940dfb2eedf0a9549eb802be7d08241b4c641d7266eb64","target":"graph","created_at":"2026-05-18T01:18:10Z","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":"We consider the random-design least-squares regression problem within the reproducing kernel Hilbert space (RKHS) framework. Given a stream of independent and identically distributed input/output data, we aim to learn a regression function within an RKHS $\\mathcal{H}$, even if the optimal predictor (i.e., the conditional expectation) is not in $\\mathcal{H}$. In a stochastic approximation framework where the estimator is updated after each observation, we show that the averaged unregularized least-mean-square algorithm (a form of stochastic gradient), given a sufficient large step-size, attains","authors_text":"Aymeric Dieuleveut, Francis Bach","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-08-02T11:22:52Z","title":"Non-parametric Stochastic Approximation with Large Step sizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.0361","kind":"arxiv","version":3},"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:e9ccced3eb912fe06ecd68187fd08933e131d39096538f7dab7093f9c870f9ff","target":"record","created_at":"2026-05-18T01:18:10Z","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":"a128419a6388a197b4a6d4461a4eea295587f47894eccdbe17ddc26574fd4020","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2014-08-02T11:22:52Z","title_canon_sha256":"9db757ed5a1be373eda1241a295e622dbf5b839a2db0deeb271874c9c8cda868"},"schema_version":"1.0","source":{"id":"1408.0361","kind":"arxiv","version":3}},"canonical_sha256":"b1cdf4549ca21a17cb87c4509973d5a155368971a38e9ac0e3ce46b6ef33687a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1cdf4549ca21a17cb87c4509973d5a155368971a38e9ac0e3ce46b6ef33687a","first_computed_at":"2026-05-18T01:18:10.307588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:18:10.307588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gqa7xRSEenX9zJon8cdOa5qYRG21qH4TBAqJ0S6WhGKrtfeRe14e6M6jJ/6RRL5zEDY7+Rea1TeqIo/VLRa3CA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:18:10.308254Z","signed_message":"canonical_sha256_bytes"},"source_id":"1408.0361","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9ccced3eb912fe06ecd68187fd08933e131d39096538f7dab7093f9c870f9ff","sha256:7ff9add60e182fb327940dfb2eedf0a9549eb802be7d08241b4c641d7266eb64"],"state_sha256":"f3f118b9d4f993f487b89759c1262ddfe0004becfba0cdf8db449bd548e45a13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSOv/7463KqN5psdbVItgn7FZByTaRw6isQgExLHNW8hdvCOAK9m3ygRy2vyOQxD87upnS3tV+kxlNw7CXv1AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:20:18.941640Z","bundle_sha256":"2e8f6c1d41705a6494faf3fe2b4311c89c3a3b15fba9fdffaba2253ab0cbd8d3"}}