{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XKIX3QN4HW3ZDDCO5N6YVPV3OT","short_pith_number":"pith:XKIX3QN4","canonical_record":{"source":{"id":"1801.07226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-22T18:14:11Z","cross_cats_sorted":["cs.AI","cs.LG","math.FA"],"title_canon_sha256":"cd8c9bd1b96b91563541ae05b9370ec09bb2d76e80fb27d771101a3fe505417c","abstract_canon_sha256":"0039c98ab609813732e1e3642031b2b1d24bb6ae979c83dd0199f7ff1c88e7c8"},"schema_version":"1.0"},"canonical_sha256":"ba917dc1bc3db7918c4eeb7d8abebb74f712c1f2cbc4a0f749c67d706eac5ea3","source":{"kind":"arxiv","id":"1801.07226","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07226","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07226v2","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07226","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"pith_short_12","alias_value":"XKIX3QN4HW3Z","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XKIX3QN4HW3ZDDCO","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XKIX3QN4","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XKIX3QN4HW3ZDDCO5N6YVPV3OT","target":"record","payload":{"canonical_record":{"source":{"id":"1801.07226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-22T18:14:11Z","cross_cats_sorted":["cs.AI","cs.LG","math.FA"],"title_canon_sha256":"cd8c9bd1b96b91563541ae05b9370ec09bb2d76e80fb27d771101a3fe505417c","abstract_canon_sha256":"0039c98ab609813732e1e3642031b2b1d24bb6ae979c83dd0199f7ff1c88e7c8"},"schema_version":"1.0"},"canonical_sha256":"ba917dc1bc3db7918c4eeb7d8abebb74f712c1f2cbc4a0f749c67d706eac5ea3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:38.745415Z","signature_b64":"rYwsRqen7wQwwc3NGrZ86/5Axx4ga6ADy22e2BZUeONEkDGm2R++PzFtkJTQWbcZXYLfMcLXUnggGIW/Ow8oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba917dc1bc3db7918c4eeb7d8abebb74f712c1f2cbc4a0f749c67d706eac5ea3","last_reissued_at":"2026-05-18T00:01:38.744961Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:38.744961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.07226","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":"2026-05-18T00:01:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Btjd5IldpLRVCrshWJPjXv3VJZm6p5WHWT3tQUfwn2dbiKZUBSOIy4GSV+OxFxTWNvsP2AfKkYLFhp5kKN4gAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:50:33.296636Z"},"content_sha256":"7ce8efdc070bc144f9d393389f66b7f492dbeb287da13695d3a45d70e38ff5c4","schema_version":"1.0","event_id":"sha256:7ce8efdc070bc144f9d393389f66b7f492dbeb287da13695d3a45d70e38ff5c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XKIX3QN4HW3ZDDCO5N6YVPV3OT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.FA"],"primary_cat":"stat.ML","authors_text":"Junhong Lin, Volkan Cevher","submitted_at":"2018-01-22T18:14:11Z","abstract_excerpt":"We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes over the data. We show that optimal generalization error bounds can be retained for distributed SGM provided that the partition level is not too large. We then extend our results to spectral-regularization algorithms (SRA), including kernel ridge regression (KRR), kernel principal component analysis, and gradient methods. Our results are super"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07226","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":"2026-05-18T00:01:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KdbXSILPEZeuNHeXEq7VHEmqaFBam3HrSGRuW2f94+4kllQyPIoGxmljBmPrcWQmXiWvhFnexM/qZpfr3EROCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T14:50:33.296974Z"},"content_sha256":"84edb977675571ec5b98294dc94b47be63e51bdf4a518bdb5fef9e420fb8ea34","schema_version":"1.0","event_id":"sha256:84edb977675571ec5b98294dc94b47be63e51bdf4a518bdb5fef9e420fb8ea34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XKIX3QN4HW3ZDDCO5N6YVPV3OT/bundle.json","state_url":"https://pith.science/pith/XKIX3QN4HW3ZDDCO5N6YVPV3OT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XKIX3QN4HW3ZDDCO5N6YVPV3OT/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":"2026-06-08T14:50:33Z","links":{"resolver":"https://pith.science/pith/XKIX3QN4HW3ZDDCO5N6YVPV3OT","bundle":"https://pith.science/pith/XKIX3QN4HW3ZDDCO5N6YVPV3OT/bundle.json","state":"https://pith.science/pith/XKIX3QN4HW3ZDDCO5N6YVPV3OT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XKIX3QN4HW3ZDDCO5N6YVPV3OT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XKIX3QN4HW3ZDDCO5N6YVPV3OT","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":"0039c98ab609813732e1e3642031b2b1d24bb6ae979c83dd0199f7ff1c88e7c8","cross_cats_sorted":["cs.AI","cs.LG","math.FA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-22T18:14:11Z","title_canon_sha256":"cd8c9bd1b96b91563541ae05b9370ec09bb2d76e80fb27d771101a3fe505417c"},"schema_version":"1.0","source":{"id":"1801.07226","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07226","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07226v2","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07226","created_at":"2026-05-18T00:01:38Z"},{"alias_kind":"pith_short_12","alias_value":"XKIX3QN4HW3Z","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XKIX3QN4HW3ZDDCO","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XKIX3QN4","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:84edb977675571ec5b98294dc94b47be63e51bdf4a518bdb5fef9e420fb8ea34","target":"graph","created_at":"2026-05-18T00:01:38Z","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 study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches and multi-passes over the data. We show that optimal generalization error bounds can be retained for distributed SGM provided that the partition level is not too large. We then extend our results to spectral-regularization algorithms (SRA), including kernel ridge regression (KRR), kernel principal component analysis, and gradient methods. Our results are super","authors_text":"Junhong Lin, Volkan Cevher","cross_cats":["cs.AI","cs.LG","math.FA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-22T18:14:11Z","title":"Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07226","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":"sha256:7ce8efdc070bc144f9d393389f66b7f492dbeb287da13695d3a45d70e38ff5c4","target":"record","created_at":"2026-05-18T00:01:38Z","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":"0039c98ab609813732e1e3642031b2b1d24bb6ae979c83dd0199f7ff1c88e7c8","cross_cats_sorted":["cs.AI","cs.LG","math.FA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-22T18:14:11Z","title_canon_sha256":"cd8c9bd1b96b91563541ae05b9370ec09bb2d76e80fb27d771101a3fe505417c"},"schema_version":"1.0","source":{"id":"1801.07226","kind":"arxiv","version":2}},"canonical_sha256":"ba917dc1bc3db7918c4eeb7d8abebb74f712c1f2cbc4a0f749c67d706eac5ea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba917dc1bc3db7918c4eeb7d8abebb74f712c1f2cbc4a0f749c67d706eac5ea3","first_computed_at":"2026-05-18T00:01:38.744961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:38.744961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rYwsRqen7wQwwc3NGrZ86/5Axx4ga6ADy22e2BZUeONEkDGm2R++PzFtkJTQWbcZXYLfMcLXUnggGIW/Ow8oDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:38.745415Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.07226","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ce8efdc070bc144f9d393389f66b7f492dbeb287da13695d3a45d70e38ff5c4","sha256:84edb977675571ec5b98294dc94b47be63e51bdf4a518bdb5fef9e420fb8ea34"],"state_sha256":"b7b0659505fbb52822f95eb19ec4bf499cef9af84614570a751957664eb5e597"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZhKxUHV7TeLY5vvFG4M2CU8eRfrfFbAVcBsYuINbH7yMxxiup9nIgrJajNTv2rjS4H5mN/aZxUhFr8ms+YcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T14:50:33.298866Z","bundle_sha256":"f7de45d7feb92170e23770514b47b0bb864490e2b06eb501456a66bb1a243e9c"}}