{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2010:TWA4XMQSTNNBATXDGL2X7P2HO2","short_pith_number":"pith:TWA4XMQS","canonical_record":{"source":{"id":"1011.0472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-01T23:41:35Z","cross_cats_sorted":[],"title_canon_sha256":"32fadd76c9594172d69e53b008552b7c33a31d69b23e5f8b3ce14158ecdc65fc","abstract_canon_sha256":"81b977d0b03ca5b36d081599cf9f0119a9c864faf479eb860e604f45588d6b5c"},"schema_version":"1.0"},"canonical_sha256":"9d81cbb2129b5a104ee332f57fbf477685ca833e595061364a9ee71305db99aa","source":{"kind":"arxiv","id":"1011.0472","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1011.0472","created_at":"2026-05-18T04:37:21Z"},{"alias_kind":"arxiv_version","alias_value":"1011.0472v1","created_at":"2026-05-18T04:37:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.0472","created_at":"2026-05-18T04:37:21Z"},{"alias_kind":"pith_short_12","alias_value":"TWA4XMQSTNNB","created_at":"2026-05-18T12:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"TWA4XMQSTNNBATXD","created_at":"2026-05-18T12:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"TWA4XMQS","created_at":"2026-05-18T12:26:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2010:TWA4XMQSTNNBATXDGL2X7P2HO2","target":"record","payload":{"canonical_record":{"source":{"id":"1011.0472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-01T23:41:35Z","cross_cats_sorted":[],"title_canon_sha256":"32fadd76c9594172d69e53b008552b7c33a31d69b23e5f8b3ce14158ecdc65fc","abstract_canon_sha256":"81b977d0b03ca5b36d081599cf9f0119a9c864faf479eb860e604f45588d6b5c"},"schema_version":"1.0"},"canonical_sha256":"9d81cbb2129b5a104ee332f57fbf477685ca833e595061364a9ee71305db99aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:37:21.646016Z","signature_b64":"7rbRxvMB0abuI389oI8jsDgJjyXt30P8SLBQ1KWOAIM2n+VWGaDVhKGNN4+k98hrmxcZUg39dFoxXlot6wTFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d81cbb2129b5a104ee332f57fbf477685ca833e595061364a9ee71305db99aa","last_reissued_at":"2026-05-18T04:37:21.645353Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:37:21.645353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1011.0472","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":"2026-05-18T04:37:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOxlfReJlXtQDxkttabSEedEWNVV4ISI97Eg3qofJw29gF2152NGk+842LNzb9h+6vM3VHch0pTPLl/9N9JlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T08:06:27.700512Z"},"content_sha256":"042962cfe161f1a90ab751060d77ab33c784985838a1e12a013bdb3434d7fbda","schema_version":"1.0","event_id":"sha256:042962cfe161f1a90ab751060d77ab33c784985838a1e12a013bdb3434d7fbda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2010:TWA4XMQSTNNBATXDGL2X7P2HO2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularized Risk Minimization by Nesterov's Accelerated Gradient Methods: Algorithmic Extensions and Empirical Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ankan Saha, S.V.N. Vishwanathan, Xinhua Zhang","submitted_at":"2010-11-01T23:41:35Z","abstract_excerpt":"Nesterov's accelerated gradient methods (AGM) have been successfully applied in many machine learning areas. However, their empirical performance on training max-margin models has been inferior to existing specialized solvers. In this paper, we first extend AGM to strongly convex and composite objective functions with Bregman style prox-functions. Our unifying framework covers both the $\\infty$-memory and 1-memory styles of AGM, tunes the Lipschiz constant adaptively, and bounds the duality gap. Then we demonstrate various ways to apply this framework of methods to a wide range of machine lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.0472","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":"2026-05-18T04:37:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lTTp/CCT5MVchrm4UxsT7v4ZROPT5em0U8TVXMBoBP8KoK7onz7OgYJvHjXHjG4jNPkYbNoPcYYfl7LO4ztHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T08:06:27.700853Z"},"content_sha256":"0c845f575a1ba7411989050ff43973882eb9a03a3a717a55c6c319eba11d9082","schema_version":"1.0","event_id":"sha256:0c845f575a1ba7411989050ff43973882eb9a03a3a717a55c6c319eba11d9082"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TWA4XMQSTNNBATXDGL2X7P2HO2/bundle.json","state_url":"https://pith.science/pith/TWA4XMQSTNNBATXDGL2X7P2HO2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TWA4XMQSTNNBATXDGL2X7P2HO2/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":"2026-05-28T08:06:27Z","links":{"resolver":"https://pith.science/pith/TWA4XMQSTNNBATXDGL2X7P2HO2","bundle":"https://pith.science/pith/TWA4XMQSTNNBATXDGL2X7P2HO2/bundle.json","state":"https://pith.science/pith/TWA4XMQSTNNBATXDGL2X7P2HO2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TWA4XMQSTNNBATXDGL2X7P2HO2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:TWA4XMQSTNNBATXDGL2X7P2HO2","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":"81b977d0b03ca5b36d081599cf9f0119a9c864faf479eb860e604f45588d6b5c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-01T23:41:35Z","title_canon_sha256":"32fadd76c9594172d69e53b008552b7c33a31d69b23e5f8b3ce14158ecdc65fc"},"schema_version":"1.0","source":{"id":"1011.0472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1011.0472","created_at":"2026-05-18T04:37:21Z"},{"alias_kind":"arxiv_version","alias_value":"1011.0472v1","created_at":"2026-05-18T04:37:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1011.0472","created_at":"2026-05-18T04:37:21Z"},{"alias_kind":"pith_short_12","alias_value":"TWA4XMQSTNNB","created_at":"2026-05-18T12:26:15Z"},{"alias_kind":"pith_short_16","alias_value":"TWA4XMQSTNNBATXD","created_at":"2026-05-18T12:26:15Z"},{"alias_kind":"pith_short_8","alias_value":"TWA4XMQS","created_at":"2026-05-18T12:26:15Z"}],"graph_snapshots":[{"event_id":"sha256:0c845f575a1ba7411989050ff43973882eb9a03a3a717a55c6c319eba11d9082","target":"graph","created_at":"2026-05-18T04:37:21Z","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":"Nesterov's accelerated gradient methods (AGM) have been successfully applied in many machine learning areas. However, their empirical performance on training max-margin models has been inferior to existing specialized solvers. In this paper, we first extend AGM to strongly convex and composite objective functions with Bregman style prox-functions. Our unifying framework covers both the $\\infty$-memory and 1-memory styles of AGM, tunes the Lipschiz constant adaptively, and bounds the duality gap. Then we demonstrate various ways to apply this framework of methods to a wide range of machine lear","authors_text":"Ankan Saha, S.V.N. Vishwanathan, Xinhua Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-01T23:41:35Z","title":"Regularized Risk Minimization by Nesterov's Accelerated Gradient Methods: Algorithmic Extensions and Empirical Studies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1011.0472","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":"sha256:042962cfe161f1a90ab751060d77ab33c784985838a1e12a013bdb3434d7fbda","target":"record","created_at":"2026-05-18T04:37:21Z","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":"81b977d0b03ca5b36d081599cf9f0119a9c864faf479eb860e604f45588d6b5c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-11-01T23:41:35Z","title_canon_sha256":"32fadd76c9594172d69e53b008552b7c33a31d69b23e5f8b3ce14158ecdc65fc"},"schema_version":"1.0","source":{"id":"1011.0472","kind":"arxiv","version":1}},"canonical_sha256":"9d81cbb2129b5a104ee332f57fbf477685ca833e595061364a9ee71305db99aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d81cbb2129b5a104ee332f57fbf477685ca833e595061364a9ee71305db99aa","first_computed_at":"2026-05-18T04:37:21.645353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:37:21.645353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7rbRxvMB0abuI389oI8jsDgJjyXt30P8SLBQ1KWOAIM2n+VWGaDVhKGNN4+k98hrmxcZUg39dFoxXlot6wTFDA==","signature_status":"signed_v1","signed_at":"2026-05-18T04:37:21.646016Z","signed_message":"canonical_sha256_bytes"},"source_id":"1011.0472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:042962cfe161f1a90ab751060d77ab33c784985838a1e12a013bdb3434d7fbda","sha256:0c845f575a1ba7411989050ff43973882eb9a03a3a717a55c6c319eba11d9082"],"state_sha256":"02eb365f6803070853c6d8850eb20f2ef75f7b22570a0a4ce2c94b5f85661a06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qskHcUGQNJiQd8AihhuSpXqRjg4APbAJ/tt+rqaV46UQZim1hXrkC1uRIpddflsyvD7YjgbBNPgQ0LsrmMVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T08:06:27.703066Z","bundle_sha256":"47c1b07477de3eb859f205ee1e96023bb3bc0ae519d404d51725573e9508fb30"}}