{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:E7UABWINO6TI3HARVXBQGA7V7E","short_pith_number":"pith:E7UABWIN","canonical_record":{"source":{"id":"2204.00006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T07:48:30Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a22cd9fd31bc9fdccc3ea28db71c06e6195df8f269ceefc1d3f5e1a5a1a5ac95","abstract_canon_sha256":"708d6be9bfffdb5e462b370f42ca4fcfafde97e4b9c3f50a1834feeae2851ab6"},"schema_version":"1.0"},"canonical_sha256":"27e800d90d77a68d9c11adc30303f5f9165baf2a777471cb6a5cb096aaa3ac7b","source":{"kind":"arxiv","id":"2204.00006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00006","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00006v1","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00006","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"E7UABWINO6TI","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"E7UABWINO6TI3HAR","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"E7UABWIN","created_at":"2026-07-05T04:10:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:E7UABWINO6TI3HARVXBQGA7V7E","target":"record","payload":{"canonical_record":{"source":{"id":"2204.00006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T07:48:30Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"a22cd9fd31bc9fdccc3ea28db71c06e6195df8f269ceefc1d3f5e1a5a1a5ac95","abstract_canon_sha256":"708d6be9bfffdb5e462b370f42ca4fcfafde97e4b9c3f50a1834feeae2851ab6"},"schema_version":"1.0"},"canonical_sha256":"27e800d90d77a68d9c11adc30303f5f9165baf2a777471cb6a5cb096aaa3ac7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:41.761586Z","signature_b64":"MIxmx9KMylM6mc4KMNN3rMxAXWcG0m7Q9PlkzqD1JShCYV9GH16kO61awRipbVqkimRUiXwR8WQq5vvjyWyiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27e800d90d77a68d9c11adc30303f5f9165baf2a777471cb6a5cb096aaa3ac7b","last_reissued_at":"2026-07-05T04:10:41.761192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:41.761192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.00006","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":"2026-07-05T04:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VicS/BzW28RUmgYfxxbAWmtLlHrUfO+uKR+9Ivdx2JatpYvP5AtmJVUladLYVU1ZKxcJuzfcxEwTvjEV0M5dAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:51:46.234999Z"},"content_sha256":"0f781685fd1441787f63317baf9e440d0f12e10c3545714856ac943097aec67f","schema_version":"1.0","event_id":"sha256:0f781685fd1441787f63317baf9e440d0f12e10c3545714856ac943097aec67f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:E7UABWINO6TI3HARVXBQGA7V7E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Sampling Affects the Complexity of Online SGD over Dependent Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Kaiyi Ji, Shaocong Ma, Yingbin Liang, Yi Zhou, Ziyi Chen","submitted_at":"2022-03-31T07:48:30Z","abstract_excerpt":"Conventional machine learning applications typically assume that data samples are independently and identically distributed (i.i.d.). However, practical scenarios often involve a data-generating process that produces highly dependent data samples, which are known to heavily bias the stochastic optimization process and slow down the convergence of learning. In this paper, we conduct a fundamental study on how different stochastic data sampling schemes affect the sample complexity of online stochastic gradient descent (SGD) over highly dependent data. Specifically, with a $\\phi$-mixing model of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00006","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.00006/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PFXt0lFR9M3K5JgoFHFKjcCKV2MWdUw0NjAjh/kh0HGfTC0XPmvu9oFi2ZYmPsbAeDsiHIjNFxGZ0mFCd1jYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:51:46.235592Z"},"content_sha256":"44296a915d62b069f4e61fec0eb618d90152fe89cf0190a5606ff8395d9d0149","schema_version":"1.0","event_id":"sha256:44296a915d62b069f4e61fec0eb618d90152fe89cf0190a5606ff8395d9d0149"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7UABWINO6TI3HARVXBQGA7V7E/bundle.json","state_url":"https://pith.science/pith/E7UABWINO6TI3HARVXBQGA7V7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7UABWINO6TI3HARVXBQGA7V7E/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":"2026-08-18T08:51:46Z","links":{"resolver":"https://pith.science/pith/E7UABWINO6TI3HARVXBQGA7V7E","bundle":"https://pith.science/pith/E7UABWINO6TI3HARVXBQGA7V7E/bundle.json","state":"https://pith.science/pith/E7UABWINO6TI3HARVXBQGA7V7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7UABWINO6TI3HARVXBQGA7V7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E7UABWINO6TI3HARVXBQGA7V7E","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":"708d6be9bfffdb5e462b370f42ca4fcfafde97e4b9c3f50a1834feeae2851ab6","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T07:48:30Z","title_canon_sha256":"a22cd9fd31bc9fdccc3ea28db71c06e6195df8f269ceefc1d3f5e1a5a1a5ac95"},"schema_version":"1.0","source":{"id":"2204.00006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00006","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00006v1","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00006","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"E7UABWINO6TI","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"E7UABWINO6TI3HAR","created_at":"2026-07-05T04:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"E7UABWIN","created_at":"2026-07-05T04:10:41Z"}],"graph_snapshots":[{"event_id":"sha256:44296a915d62b069f4e61fec0eb618d90152fe89cf0190a5606ff8395d9d0149","target":"graph","created_at":"2026-07-05T04:10:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.00006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional machine learning applications typically assume that data samples are independently and identically distributed (i.i.d.). However, practical scenarios often involve a data-generating process that produces highly dependent data samples, which are known to heavily bias the stochastic optimization process and slow down the convergence of learning. In this paper, we conduct a fundamental study on how different stochastic data sampling schemes affect the sample complexity of online stochastic gradient descent (SGD) over highly dependent data. Specifically, with a $\\phi$-mixing model of ","authors_text":"Kaiyi Ji, Shaocong Ma, Yingbin Liang, Yi Zhou, Ziyi Chen","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T07:48:30Z","title":"Data Sampling Affects the Complexity of Online SGD over Dependent Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00006","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":"sha256:0f781685fd1441787f63317baf9e440d0f12e10c3545714856ac943097aec67f","target":"record","created_at":"2026-07-05T04:10:41Z","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":"708d6be9bfffdb5e462b370f42ca4fcfafde97e4b9c3f50a1834feeae2851ab6","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-31T07:48:30Z","title_canon_sha256":"a22cd9fd31bc9fdccc3ea28db71c06e6195df8f269ceefc1d3f5e1a5a1a5ac95"},"schema_version":"1.0","source":{"id":"2204.00006","kind":"arxiv","version":1}},"canonical_sha256":"27e800d90d77a68d9c11adc30303f5f9165baf2a777471cb6a5cb096aaa3ac7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27e800d90d77a68d9c11adc30303f5f9165baf2a777471cb6a5cb096aaa3ac7b","first_computed_at":"2026-07-05T04:10:41.761192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:41.761192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MIxmx9KMylM6mc4KMNN3rMxAXWcG0m7Q9PlkzqD1JShCYV9GH16kO61awRipbVqkimRUiXwR8WQq5vvjyWyiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:41.761586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f781685fd1441787f63317baf9e440d0f12e10c3545714856ac943097aec67f","sha256:44296a915d62b069f4e61fec0eb618d90152fe89cf0190a5606ff8395d9d0149"],"state_sha256":"d8fe85195b67374e44e178ed54224ec45c6afca5a03845c337dbd9a3d3e28dc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xOJOioTdbd18uDFH82/QOZuzKVjXy4Fk/fB/Q7IqWsq2NqMhpZepG48ImAeIQlrxnEE3Ywi4t0RaDRVZvJwjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:51:46.241966Z","bundle_sha256":"bfd1f0ccbb06a61cd6a962d1d8f7dee1887282ab756b85cc0fb49b961b7ae6cf"}}