{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5K5BLIOWRKSSEKSLM4CS53TOOQ","short_pith_number":"pith:5K5BLIOW","canonical_record":{"source":{"id":"1709.02726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-08T14:54:44Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fa452553b5deeeb7e3c88f60455b527be0622b34e43939d4fbfdebddb79da7ad","abstract_canon_sha256":"f41dc59eeb231dc57bd7e8ffe7b1abc6953e8a6864b3c49ae3c1435e146aaf24"},"schema_version":"1.0"},"canonical_sha256":"eaba15a1d68aa5222a4b67052eee6e7423d52a7744c929e2234306162b5eb5c4","source":{"kind":"arxiv","id":"1709.02726","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02726","created_at":"2026-05-18T00:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02726v1","created_at":"2026-05-18T00:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02726","created_at":"2026-05-18T00:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"5K5BLIOWRKSS","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5K5BLIOWRKSSEKSL","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5K5BLIOW","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5K5BLIOWRKSSEKSLM4CS53TOOQ","target":"record","payload":{"canonical_record":{"source":{"id":"1709.02726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-08T14:54:44Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fa452553b5deeeb7e3c88f60455b527be0622b34e43939d4fbfdebddb79da7ad","abstract_canon_sha256":"f41dc59eeb231dc57bd7e8ffe7b1abc6953e8a6864b3c49ae3c1435e146aaf24"},"schema_version":"1.0"},"canonical_sha256":"eaba15a1d68aa5222a4b67052eee6e7423d52a7744c929e2234306162b5eb5c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:40.487355Z","signature_b64":"+nWHuZizj39/GBnIKxl3bEcCCIVIhvBJ4/sYoeKZdjiM7Sw2x1wM1N9/vHZaDAHAS9BAFFlTP/4moNymTl75Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaba15a1d68aa5222a4b67052eee6e7423d52a7744c929e2234306162b5eb5c4","last_reissued_at":"2026-05-18T00:35:40.486643Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:40.486643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.02726","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":"2026-05-18T00:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CwEVpgB8senBoL8AiKugChFvBZ8eoGjeQLfLUadDVwp+W8h+VA3rRPAwk34WO3Hy/WxbX+D3WyheGK/Ce+ujCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:13:16.005843Z"},"content_sha256":"b67486c5ea831d56d2a3c3a23c99ac12fb32dc405db003b04424f29ccf381fe4","schema_version":"1.0","event_id":"sha256:b67486c5ea831d56d2a3c3a23c99ac12fb32dc405db003b04424f29ccf381fe4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5K5BLIOWRKSSEKSLM4CS53TOOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Pooria Joulani","submitted_at":"2017-09-08T14:54:44Z","abstract_excerpt":"Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a generalization of Bregman divergences, we provide a self-contained, modular analysis of the two workhorses of online learning: (general) adaptive versions of Mirror Descent (MD) and the Follow-the-Regularized-Leader (FTRL) algorithms. The analysis is done with extra care so as not to introduce assumptions not needed in the proofs and allows to combine, in a straigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02726","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":"2026-05-18T00:35:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rOg6haVFF6N8VcfLjGl5WS5Vm5FvohOzUwGE9EyGAFuo6DsgS6Qb/Ln/zA7HEEi8fM4RqfxriRy3vkACn2AHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T21:13:16.006535Z"},"content_sha256":"64dc03ba0f6ea39426957624c02bcded8f8ecc6989c124deab212a626c7da438","schema_version":"1.0","event_id":"sha256:64dc03ba0f6ea39426957624c02bcded8f8ecc6989c124deab212a626c7da438"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5K5BLIOWRKSSEKSLM4CS53TOOQ/bundle.json","state_url":"https://pith.science/pith/5K5BLIOWRKSSEKSLM4CS53TOOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5K5BLIOWRKSSEKSLM4CS53TOOQ/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":"2026-06-06T21:13:16Z","links":{"resolver":"https://pith.science/pith/5K5BLIOWRKSSEKSLM4CS53TOOQ","bundle":"https://pith.science/pith/5K5BLIOWRKSSEKSLM4CS53TOOQ/bundle.json","state":"https://pith.science/pith/5K5BLIOWRKSSEKSLM4CS53TOOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5K5BLIOWRKSSEKSLM4CS53TOOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5K5BLIOWRKSSEKSLM4CS53TOOQ","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":"f41dc59eeb231dc57bd7e8ffe7b1abc6953e8a6864b3c49ae3c1435e146aaf24","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-08T14:54:44Z","title_canon_sha256":"fa452553b5deeeb7e3c88f60455b527be0622b34e43939d4fbfdebddb79da7ad"},"schema_version":"1.0","source":{"id":"1709.02726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.02726","created_at":"2026-05-18T00:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"1709.02726v1","created_at":"2026-05-18T00:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.02726","created_at":"2026-05-18T00:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"5K5BLIOWRKSS","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5K5BLIOWRKSSEKSL","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5K5BLIOW","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:64dc03ba0f6ea39426957624c02bcded8f8ecc6989c124deab212a626c7da438","target":"graph","created_at":"2026-05-18T00:35:40Z","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":"Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a generalization of Bregman divergences, we provide a self-contained, modular analysis of the two workhorses of online learning: (general) adaptive versions of Mirror Descent (MD) and the Follow-the-Regularized-Leader (FTRL) algorithms. The analysis is done with extra care so as not to introduce assumptions not needed in the proofs and allows to combine, in a straigh","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Pooria Joulani","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-08T14:54:44Z","title":"A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.02726","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:b67486c5ea831d56d2a3c3a23c99ac12fb32dc405db003b04424f29ccf381fe4","target":"record","created_at":"2026-05-18T00:35:40Z","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":"f41dc59eeb231dc57bd7e8ffe7b1abc6953e8a6864b3c49ae3c1435e146aaf24","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-08T14:54:44Z","title_canon_sha256":"fa452553b5deeeb7e3c88f60455b527be0622b34e43939d4fbfdebddb79da7ad"},"schema_version":"1.0","source":{"id":"1709.02726","kind":"arxiv","version":1}},"canonical_sha256":"eaba15a1d68aa5222a4b67052eee6e7423d52a7744c929e2234306162b5eb5c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eaba15a1d68aa5222a4b67052eee6e7423d52a7744c929e2234306162b5eb5c4","first_computed_at":"2026-05-18T00:35:40.486643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:40.486643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+nWHuZizj39/GBnIKxl3bEcCCIVIhvBJ4/sYoeKZdjiM7Sw2x1wM1N9/vHZaDAHAS9BAFFlTP/4moNymTl75Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:40.487355Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.02726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b67486c5ea831d56d2a3c3a23c99ac12fb32dc405db003b04424f29ccf381fe4","sha256:64dc03ba0f6ea39426957624c02bcded8f8ecc6989c124deab212a626c7da438"],"state_sha256":"bb0946f8ea9fb42e8998c94afd71a45671399b2d10506b3b69f3ac3c0bf8be56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qzIdIA/P1+vXLbWhAxnTK5zbS7zXmmIxt1Y4AGUbde5xzxnKr1fLoWoK6a4SMjJZA1ixAEbQT6eJvWki3aQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T21:13:16.010366Z","bundle_sha256":"e2c46297caf6847d912dee29b9e2a0bdc7b322cbd51482e7319e6ac3c5052c95"}}