{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:PI6XZTAHZLOUE5XLEYRN3PRIB6","short_pith_number":"pith:PI6XZTAH","canonical_record":{"source":{"id":"1609.02383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-08T11:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"8b8648836da00d975f5d13e3979762ef0b3950e23631395fe66a75f8796572d1","abstract_canon_sha256":"ef938e3a9baed2856a50debd5cfc36d2dc04236611b25f77a18620dcfd74194a"},"schema_version":"1.0"},"canonical_sha256":"7a3d7ccc07cadd4276eb2622ddbe280fa84fd0f7455a93e60c0ffdf424217784","source":{"kind":"arxiv","id":"1609.02383","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.02383","created_at":"2026-05-18T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"1609.02383v1","created_at":"2026-05-18T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.02383","created_at":"2026-05-18T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"PI6XZTAHZLOU","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PI6XZTAHZLOUE5XL","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PI6XZTAH","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:PI6XZTAHZLOUE5XLEYRN3PRIB6","target":"record","payload":{"canonical_record":{"source":{"id":"1609.02383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-08T11:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"8b8648836da00d975f5d13e3979762ef0b3950e23631395fe66a75f8796572d1","abstract_canon_sha256":"ef938e3a9baed2856a50debd5cfc36d2dc04236611b25f77a18620dcfd74194a"},"schema_version":"1.0"},"canonical_sha256":"7a3d7ccc07cadd4276eb2622ddbe280fa84fd0f7455a93e60c0ffdf424217784","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:54.811447Z","signature_b64":"JCf9dNIXUU6BeDzhdyYhF8XYfX3JEcEb8BI+507H+TLKnTvVrzheH/YU+B8Z6bsCP37ggO2/yXj2klcUF7/uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a3d7ccc07cadd4276eb2622ddbe280fa84fd0f7455a93e60c0ffdf424217784","last_reissued_at":"2026-05-18T01:04:54.810824Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:54.810824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.02383","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":"2026-05-18T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J0qCUcwjL3WHsl0hm39kAhNOyrmSUjuGJdWjwkU721rv5raIbW66uJOpVRNx705xBV+VaZCsMj9hdmnrlL2hCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-19T22:58:07.381681Z"},"content_sha256":"1b65b4e8fc1ec7a54e4c56d49a1208c3f018337dc7c99753a7bfdbf38381ae6d","schema_version":"1.0","event_id":"sha256:1b65b4e8fc1ec7a54e4c56d49a1208c3f018337dc7c99753a7bfdbf38381ae6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:PI6XZTAHZLOUE5XLEYRN3PRIB6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Optimistic Mirror Descent for Sparsity and Curvature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Parameswaran Kamalaruban","submitted_at":"2016-09-08T11:52:05Z","abstract_excerpt":"Online Convex Optimization plays a key role in large scale machine learning. Early approaches to this problem were conservative, in which the main focus was protection against the worst case scenario. But recently several algorithms have been developed for tightening the regret bounds in easy data instances such as sparsity, predictable sequences, and curved losses. In this work we unify some of these existing techniques to obtain new update rules for the cases when these easy instances occur together. First we analyse an adaptive and optimistic update rule which achieves tighter regret bound "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.02383","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":"2026-05-18T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QEA2bKxBPKZGX6NRIjKpeV9nl6/49VvnX+jCCI44hzbRxQqODyGmd/Hg6x46pz2Fgna9j37wTgFjYN0aEZf3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-19T22:58:07.382024Z"},"content_sha256":"2938816599fb5783e30a9a637f5dffe0c9cd458524c5a2f6e6ca170f660eb928","schema_version":"1.0","event_id":"sha256:2938816599fb5783e30a9a637f5dffe0c9cd458524c5a2f6e6ca170f660eb928"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PI6XZTAHZLOUE5XLEYRN3PRIB6/bundle.json","state_url":"https://pith.science/pith/PI6XZTAHZLOUE5XLEYRN3PRIB6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PI6XZTAHZLOUE5XLEYRN3PRIB6/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":"2026-06-19T22:58:07Z","links":{"resolver":"https://pith.science/pith/PI6XZTAHZLOUE5XLEYRN3PRIB6","bundle":"https://pith.science/pith/PI6XZTAHZLOUE5XLEYRN3PRIB6/bundle.json","state":"https://pith.science/pith/PI6XZTAHZLOUE5XLEYRN3PRIB6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PI6XZTAHZLOUE5XLEYRN3PRIB6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:PI6XZTAHZLOUE5XLEYRN3PRIB6","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":"ef938e3a9baed2856a50debd5cfc36d2dc04236611b25f77a18620dcfd74194a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-08T11:52:05Z","title_canon_sha256":"8b8648836da00d975f5d13e3979762ef0b3950e23631395fe66a75f8796572d1"},"schema_version":"1.0","source":{"id":"1609.02383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.02383","created_at":"2026-05-18T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"1609.02383v1","created_at":"2026-05-18T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.02383","created_at":"2026-05-18T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"PI6XZTAHZLOU","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PI6XZTAHZLOUE5XL","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PI6XZTAH","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:2938816599fb5783e30a9a637f5dffe0c9cd458524c5a2f6e6ca170f660eb928","target":"graph","created_at":"2026-05-18T01:04:54Z","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":"Online Convex Optimization plays a key role in large scale machine learning. Early approaches to this problem were conservative, in which the main focus was protection against the worst case scenario. But recently several algorithms have been developed for tightening the regret bounds in easy data instances such as sparsity, predictable sequences, and curved losses. In this work we unify some of these existing techniques to obtain new update rules for the cases when these easy instances occur together. First we analyse an adaptive and optimistic update rule which achieves tighter regret bound ","authors_text":"Parameswaran Kamalaruban","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-08T11:52:05Z","title":"Improved Optimistic Mirror Descent for Sparsity and Curvature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.02383","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":"sha256:1b65b4e8fc1ec7a54e4c56d49a1208c3f018337dc7c99753a7bfdbf38381ae6d","target":"record","created_at":"2026-05-18T01:04:54Z","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":"ef938e3a9baed2856a50debd5cfc36d2dc04236611b25f77a18620dcfd74194a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-08T11:52:05Z","title_canon_sha256":"8b8648836da00d975f5d13e3979762ef0b3950e23631395fe66a75f8796572d1"},"schema_version":"1.0","source":{"id":"1609.02383","kind":"arxiv","version":1}},"canonical_sha256":"7a3d7ccc07cadd4276eb2622ddbe280fa84fd0f7455a93e60c0ffdf424217784","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a3d7ccc07cadd4276eb2622ddbe280fa84fd0f7455a93e60c0ffdf424217784","first_computed_at":"2026-05-18T01:04:54.810824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:54.810824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JCf9dNIXUU6BeDzhdyYhF8XYfX3JEcEb8BI+507H+TLKnTvVrzheH/YU+B8Z6bsCP37ggO2/yXj2klcUF7/uBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:54.811447Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.02383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b65b4e8fc1ec7a54e4c56d49a1208c3f018337dc7c99753a7bfdbf38381ae6d","sha256:2938816599fb5783e30a9a637f5dffe0c9cd458524c5a2f6e6ca170f660eb928"],"state_sha256":"4926377af803eb734a8ad23539381f8a4ba19c30039030d96b8574f220127dc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPMX2IQZAJqaIHKUmqMRYDB0yYbLCwRgBg5Cn7oGpJdqUNrheSR1Ijf2x3EyTkpegN13fA9e7cVw2HvpWt/nBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-19T22:58:07.384156Z","bundle_sha256":"5fbacfceaefae3858d179c1b03cab11b1ab6506bdc29a9cbd4e5eee5db2e4066"}}