{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OASKPFEVZYWU6TSYMSSO4ECUXG","short_pith_number":"pith:OASKPFEV","canonical_record":{"source":{"id":"1809.04216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-12T01:39:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"12b301fc07e4c6c4eba7341e8975cf1a8ac8cbea7d4752c822b639e52bbea9d7","abstract_canon_sha256":"4f6bb141758914f8a25d773ae9919b60bce7590b1b1d99cfbea478bea4ecabc2"},"schema_version":"1.0"},"canonical_sha256":"7024a79495ce2d4f4e5864a4ee1054b9a0d4e7811c37c8acc56d368c1b94d8ae","source":{"kind":"arxiv","id":"1809.04216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04216","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04216v1","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04216","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"OASKPFEVZYWU","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OASKPFEVZYWU6TSY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OASKPFEV","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OASKPFEVZYWU6TSYMSSO4ECUXG","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-12T01:39:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"12b301fc07e4c6c4eba7341e8975cf1a8ac8cbea7d4752c822b639e52bbea9d7","abstract_canon_sha256":"4f6bb141758914f8a25d773ae9919b60bce7590b1b1d99cfbea478bea4ecabc2"},"schema_version":"1.0"},"canonical_sha256":"7024a79495ce2d4f4e5864a4ee1054b9a0d4e7811c37c8acc56d368c1b94d8ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:55.157040Z","signature_b64":"aD0890yz+3vcPDdQYFmhdj3eR3HWlahu7Dy0SzzDqX7ymcwC3KRbM1ZujCfbuO+gy5dkvcWOISuilVCqBIaVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7024a79495ce2d4f4e5864a4ee1054b9a0d4e7811c37c8acc56d368c1b94d8ae","last_reissued_at":"2026-05-18T00:05:55.156436Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:55.156436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04216","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":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rjZOUiqV6xnTibobqz4Wr72DTcB1+TrMfyJ+0gT29MGEYFxXbJet1u3h6rdUkS8KKTf8xDin5tx5OCovuBYWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:35:39.360417Z"},"content_sha256":"16f209b77d85b6b1c4d802aabfccdb2e44dbe0bc887ae468c59ad1c8f955f117","schema_version":"1.0","event_id":"sha256:16f209b77d85b6b1c4d802aabfccdb2e44dbe0bc887ae468c59ad1c8f955f117"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OASKPFEVZYWU6TSYMSSO4ECUXG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Markov Chain Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Tao Sun, Wotao Yin, Yuejiao Sun","submitted_at":"2018-09-12T01:39:13Z","abstract_excerpt":"Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the trajectory of a Markov chain. Existing results of this method assume convex objectives and a reversible Markov chain and thus have their limitations. We establish new non-ergodic convergence under wider step sizes, for nonconvex problems, and for non-reversible finite-state Markov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04216","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":""},"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":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zddXHRYcrGVaO2GHcDlIqOuRfmEsv4W1Md8hqV8KwPyW9it+abzXTUa3lqo9iF3tOZILIc2ZTNANhYHtNpbtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:35:39.361185Z"},"content_sha256":"2d753118ebdeec1935eaaacbfcea5beda2826d2c53f601de5a9888db7767c355","schema_version":"1.0","event_id":"sha256:2d753118ebdeec1935eaaacbfcea5beda2826d2c53f601de5a9888db7767c355"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OASKPFEVZYWU6TSYMSSO4ECUXG/bundle.json","state_url":"https://pith.science/pith/OASKPFEVZYWU6TSYMSSO4ECUXG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OASKPFEVZYWU6TSYMSSO4ECUXG/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":"2026-05-30T08:35:39Z","links":{"resolver":"https://pith.science/pith/OASKPFEVZYWU6TSYMSSO4ECUXG","bundle":"https://pith.science/pith/OASKPFEVZYWU6TSYMSSO4ECUXG/bundle.json","state":"https://pith.science/pith/OASKPFEVZYWU6TSYMSSO4ECUXG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OASKPFEVZYWU6TSYMSSO4ECUXG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OASKPFEVZYWU6TSYMSSO4ECUXG","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":"4f6bb141758914f8a25d773ae9919b60bce7590b1b1d99cfbea478bea4ecabc2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-12T01:39:13Z","title_canon_sha256":"12b301fc07e4c6c4eba7341e8975cf1a8ac8cbea7d4752c822b639e52bbea9d7"},"schema_version":"1.0","source":{"id":"1809.04216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04216","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04216v1","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04216","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"OASKPFEVZYWU","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OASKPFEVZYWU6TSY","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OASKPFEV","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:2d753118ebdeec1935eaaacbfcea5beda2826d2c53f601de5a9888db7767c355","target":"graph","created_at":"2026-05-18T00:05:55Z","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":"Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the trajectory of a Markov chain. Existing results of this method assume convex objectives and a reversible Markov chain and thus have their limitations. We establish new non-ergodic convergence under wider step sizes, for nonconvex problems, and for non-reversible finite-state Markov","authors_text":"Tao Sun, Wotao Yin, Yuejiao Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-12T01:39:13Z","title":"On Markov Chain Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04216","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":"sha256:16f209b77d85b6b1c4d802aabfccdb2e44dbe0bc887ae468c59ad1c8f955f117","target":"record","created_at":"2026-05-18T00:05:55Z","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":"4f6bb141758914f8a25d773ae9919b60bce7590b1b1d99cfbea478bea4ecabc2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-12T01:39:13Z","title_canon_sha256":"12b301fc07e4c6c4eba7341e8975cf1a8ac8cbea7d4752c822b639e52bbea9d7"},"schema_version":"1.0","source":{"id":"1809.04216","kind":"arxiv","version":1}},"canonical_sha256":"7024a79495ce2d4f4e5864a4ee1054b9a0d4e7811c37c8acc56d368c1b94d8ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7024a79495ce2d4f4e5864a4ee1054b9a0d4e7811c37c8acc56d368c1b94d8ae","first_computed_at":"2026-05-18T00:05:55.156436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:55.156436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aD0890yz+3vcPDdQYFmhdj3eR3HWlahu7Dy0SzzDqX7ymcwC3KRbM1ZujCfbuO+gy5dkvcWOISuilVCqBIaVAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:55.157040Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16f209b77d85b6b1c4d802aabfccdb2e44dbe0bc887ae468c59ad1c8f955f117","sha256:2d753118ebdeec1935eaaacbfcea5beda2826d2c53f601de5a9888db7767c355"],"state_sha256":"2b8ce795de84ced7280f07fa488c7c0b647f431731924fbab6ea7a3b283682b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYGEHt4EGWLPrXA/WsQuJUQO/17BAmV+KpTyH0fm5zfjTJQbD6ky1P+FS7MOxSg0Vv4lvcRmEOXR4oZZUW/wBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:35:39.366872Z","bundle_sha256":"0d4f67d6b55200e170d8814a02ec690e3a07d288759b63ef6743e650f78ed94c"}}