{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:R2U56D5NM4YK4GDXDYTWI7QIHG","short_pith_number":"pith:R2U56D5N","canonical_record":{"source":{"id":"1904.09369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T23:24:38Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"8b819b852c2edd9bc68354b7434ab2305786420d95d0272a4d313e9caa1f1b46","abstract_canon_sha256":"97d0e673fc29f7d79d4aa3c17d3cdb0cff376068732ba8d4f3349e287f7e7862"},"schema_version":"1.0"},"canonical_sha256":"8ea9df0fad6730ae18771e27647e0839aa2646efc8f017620ec7410bb670f531","source":{"kind":"arxiv","id":"1904.09369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09369","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09369v1","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09369","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"pith_short_12","alias_value":"R2U56D5NM4YK","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R2U56D5NM4YK4GDX","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R2U56D5N","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:R2U56D5NM4YK4GDXDYTWI7QIHG","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T23:24:38Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"8b819b852c2edd9bc68354b7434ab2305786420d95d0272a4d313e9caa1f1b46","abstract_canon_sha256":"97d0e673fc29f7d79d4aa3c17d3cdb0cff376068732ba8d4f3349e287f7e7862"},"schema_version":"1.0"},"canonical_sha256":"8ea9df0fad6730ae18771e27647e0839aa2646efc8f017620ec7410bb670f531","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:07.268274Z","signature_b64":"7Py36lrO0TYhcb6uXKl2C1AaBEaOvRezkiwyr7WRCrQwwC4lxW9peu4kmZ3EldFJYnsIjtelrRHVDU2ZW1VvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ea9df0fad6730ae18771e27647e0839aa2646efc8f017620ec7410bb670f531","last_reissued_at":"2026-05-17T23:48:07.267840Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:07.267840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09369","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":"2026-05-17T23:48:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UptJ2/LO9D3T3sZG2rR3KYLgM7ZoByU0bZfF4X3RJdBBFjnkPcFHQJ1Y/1ep62p2J+LrPZshMb6BzyqUznqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T09:23:50.550777Z"},"content_sha256":"4625162346198aeaadc6c1d59e3084e676039ea4b0f53f736e2efeeea50a84ed","schema_version":"1.0","event_id":"sha256:4625162346198aeaadc6c1d59e3084e676039ea4b0f53f736e2efeeea50a84ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:R2U56D5NM4YK4GDXDYTWI7QIHG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimax Optimal Online Stochastic Learning for Sequences of Convex Functions under Sub-Gradient Observation Failures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hakan Gokcesu, Suleyman S. Kozat","submitted_at":"2019-04-19T23:24:38Z","abstract_excerpt":"We study online convex optimization under stochastic sub-gradient observation faults, where we introduce adaptive algorithms with minimax optimal regret guarantees. We specifically study scenarios where our sub-gradient observations can be noisy or even completely missing in a stochastic manner. To this end, we propose algorithms based on sub-gradient descent method, which achieve tight minimax optimal regret bounds. When necessary, these algorithms utilize properties of the underlying stochastic settings to optimize their learning rates (step sizes). These optimizations are the main factor in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09369","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":"2026-05-17T23:48:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGDu+bzwoJOMpt+HVp2UubV1aUJcBPYbW56fulOzvf53vJYxc6+2lQFdjFC+ShIhicfvJJULRVfc+Z1qWAPKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T09:23:50.551115Z"},"content_sha256":"b1fef281f433b9af5ca6ca3173d02b9e07b35a364bd355dcf2446c79bc38c59e","schema_version":"1.0","event_id":"sha256:b1fef281f433b9af5ca6ca3173d02b9e07b35a364bd355dcf2446c79bc38c59e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2U56D5NM4YK4GDXDYTWI7QIHG/bundle.json","state_url":"https://pith.science/pith/R2U56D5NM4YK4GDXDYTWI7QIHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2U56D5NM4YK4GDXDYTWI7QIHG/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":"2026-06-02T09:23:50Z","links":{"resolver":"https://pith.science/pith/R2U56D5NM4YK4GDXDYTWI7QIHG","bundle":"https://pith.science/pith/R2U56D5NM4YK4GDXDYTWI7QIHG/bundle.json","state":"https://pith.science/pith/R2U56D5NM4YK4GDXDYTWI7QIHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2U56D5NM4YK4GDXDYTWI7QIHG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R2U56D5NM4YK4GDXDYTWI7QIHG","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":"97d0e673fc29f7d79d4aa3c17d3cdb0cff376068732ba8d4f3349e287f7e7862","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T23:24:38Z","title_canon_sha256":"8b819b852c2edd9bc68354b7434ab2305786420d95d0272a4d313e9caa1f1b46"},"schema_version":"1.0","source":{"id":"1904.09369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09369","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09369v1","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09369","created_at":"2026-05-17T23:48:07Z"},{"alias_kind":"pith_short_12","alias_value":"R2U56D5NM4YK","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"R2U56D5NM4YK4GDX","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"R2U56D5N","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:b1fef281f433b9af5ca6ca3173d02b9e07b35a364bd355dcf2446c79bc38c59e","target":"graph","created_at":"2026-05-17T23:48:07Z","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 online convex optimization under stochastic sub-gradient observation faults, where we introduce adaptive algorithms with minimax optimal regret guarantees. We specifically study scenarios where our sub-gradient observations can be noisy or even completely missing in a stochastic manner. To this end, we propose algorithms based on sub-gradient descent method, which achieve tight minimax optimal regret bounds. When necessary, these algorithms utilize properties of the underlying stochastic settings to optimize their learning rates (step sizes). These optimizations are the main factor in","authors_text":"Hakan Gokcesu, Suleyman S. Kozat","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T23:24:38Z","title":"Minimax Optimal Online Stochastic Learning for Sequences of Convex Functions under Sub-Gradient Observation Failures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09369","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":"sha256:4625162346198aeaadc6c1d59e3084e676039ea4b0f53f736e2efeeea50a84ed","target":"record","created_at":"2026-05-17T23:48:07Z","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":"97d0e673fc29f7d79d4aa3c17d3cdb0cff376068732ba8d4f3349e287f7e7862","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T23:24:38Z","title_canon_sha256":"8b819b852c2edd9bc68354b7434ab2305786420d95d0272a4d313e9caa1f1b46"},"schema_version":"1.0","source":{"id":"1904.09369","kind":"arxiv","version":1}},"canonical_sha256":"8ea9df0fad6730ae18771e27647e0839aa2646efc8f017620ec7410bb670f531","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ea9df0fad6730ae18771e27647e0839aa2646efc8f017620ec7410bb670f531","first_computed_at":"2026-05-17T23:48:07.267840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:07.267840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Py36lrO0TYhcb6uXKl2C1AaBEaOvRezkiwyr7WRCrQwwC4lxW9peu4kmZ3EldFJYnsIjtelrRHVDU2ZW1VvAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:07.268274Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4625162346198aeaadc6c1d59e3084e676039ea4b0f53f736e2efeeea50a84ed","sha256:b1fef281f433b9af5ca6ca3173d02b9e07b35a364bd355dcf2446c79bc38c59e"],"state_sha256":"2c5c3a031cff81fa724e795b283a1cf9fc4e03255eeb7f961c1cbf80fa8b9455"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wU/ObJmcXNgkVcS6oGcS8H0UPraDd0jAWZJhG4RZMVUDENmYMR4iIoYXXNn73Lg0Nl9ykouboL3Bc2kR5RR2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T09:23:50.553286Z","bundle_sha256":"d191c0a54e1b40191164be7d4be0c9e31b3948e6ceef2f6e5c068a8764034e65"}}