{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:HH534UEA2KRZ6Y2Z76FIEZ5SO4","short_pith_number":"pith:HH534UEA","canonical_record":{"source":{"id":"1605.06561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T23:46:58Z","cross_cats_sorted":[],"title_canon_sha256":"e2a2e9478a54ef0ccdc0860c80d4781d78539da93058b2ac2a5321db1dc24650","abstract_canon_sha256":"ae5e64c1bef0e65e1d3113c72f9aabea3e0bc2d78018af4f1b9346285fe15eda"},"schema_version":"1.0"},"canonical_sha256":"39fbbe5080d2a39f6359ff8a8267b277137517995cb2785f6623e00013fc836d","source":{"kind":"arxiv","id":"1605.06561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06561","created_at":"2026-05-18T01:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06561v1","created_at":"2026-05-18T01:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06561","created_at":"2026-05-18T01:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"HH534UEA2KRZ","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HH534UEA2KRZ6Y2Z","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HH534UEA","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:HH534UEA2KRZ6Y2Z76FIEZ5SO4","target":"record","payload":{"canonical_record":{"source":{"id":"1605.06561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T23:46:58Z","cross_cats_sorted":[],"title_canon_sha256":"e2a2e9478a54ef0ccdc0860c80d4781d78539da93058b2ac2a5321db1dc24650","abstract_canon_sha256":"ae5e64c1bef0e65e1d3113c72f9aabea3e0bc2d78018af4f1b9346285fe15eda"},"schema_version":"1.0"},"canonical_sha256":"39fbbe5080d2a39f6359ff8a8267b277137517995cb2785f6623e00013fc836d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:11.874889Z","signature_b64":"qxZYXaJCtkeG4AbuZroBZBJTrQ8bKr8pcsaOdqhS5YfAzzh2NEfRCWu/kxUL/s1Ru2hT5ZZW57VhA4U5EGUnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39fbbe5080d2a39f6359ff8a8267b277137517995cb2785f6623e00013fc836d","last_reissued_at":"2026-05-18T01:14:11.874398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:11.874398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.06561","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":"2026-05-18T01:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nb4JboQw2qlsYr4LzsSBVCSY4h+7tez1HF7BuIiJqf6lYMFPkYGlbjK7NEcn/Ux3DuKQHgTzu8KI+oubp968Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:36:20.546944Z"},"content_sha256":"5481750dc00e06d88f03ebbb7cba417711b4ca40d139fa8a8f58bd4014cc5c8d","schema_version":"1.0","event_id":"sha256:5481750dc00e06d88f03ebbb7cba417711b4ca40d139fa8a8f58bd4014cc5c8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:HH534UEA2KRZ6Y2Z76FIEZ5SO4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DynaNewton - Accelerating Newton's Method for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Hadi Daneshmand, Thomas Hofmann","submitted_at":"2016-05-20T23:46:58Z","abstract_excerpt":"Newton's method is a fundamental technique in optimization with quadratic convergence within a neighborhood around the optimum. However reaching this neighborhood is often slow and dominates the computational costs. We exploit two properties specific to empirical risk minimization problems to accelerate Newton's method, namely, subsampling training data and increasing strong convexity through regularization. We propose a novel continuation method, where we define a family of objectives over increasing sample sizes and with decreasing regularization strength. Solutions on this path are tracked "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06561","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":"2026-05-18T01:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/v/xnuj0OubobcHmxf6uJBkZVInq88SeXzo1Hz3KaBsNAg89UNPhSjxinl/5G81ziI61VnALNMuAHSJfUgPNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T00:36:20.547602Z"},"content_sha256":"d482558d47ac885180a22dee61cdee1cd47a6c96cadf0ea69f02224248f9d33a","schema_version":"1.0","event_id":"sha256:d482558d47ac885180a22dee61cdee1cd47a6c96cadf0ea69f02224248f9d33a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HH534UEA2KRZ6Y2Z76FIEZ5SO4/bundle.json","state_url":"https://pith.science/pith/HH534UEA2KRZ6Y2Z76FIEZ5SO4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HH534UEA2KRZ6Y2Z76FIEZ5SO4/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":"2026-05-27T00:36:20Z","links":{"resolver":"https://pith.science/pith/HH534UEA2KRZ6Y2Z76FIEZ5SO4","bundle":"https://pith.science/pith/HH534UEA2KRZ6Y2Z76FIEZ5SO4/bundle.json","state":"https://pith.science/pith/HH534UEA2KRZ6Y2Z76FIEZ5SO4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HH534UEA2KRZ6Y2Z76FIEZ5SO4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:HH534UEA2KRZ6Y2Z76FIEZ5SO4","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":"ae5e64c1bef0e65e1d3113c72f9aabea3e0bc2d78018af4f1b9346285fe15eda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T23:46:58Z","title_canon_sha256":"e2a2e9478a54ef0ccdc0860c80d4781d78539da93058b2ac2a5321db1dc24650"},"schema_version":"1.0","source":{"id":"1605.06561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06561","created_at":"2026-05-18T01:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06561v1","created_at":"2026-05-18T01:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06561","created_at":"2026-05-18T01:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"HH534UEA2KRZ","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HH534UEA2KRZ6Y2Z","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HH534UEA","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:d482558d47ac885180a22dee61cdee1cd47a6c96cadf0ea69f02224248f9d33a","target":"graph","created_at":"2026-05-18T01:14:11Z","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":"Newton's method is a fundamental technique in optimization with quadratic convergence within a neighborhood around the optimum. However reaching this neighborhood is often slow and dominates the computational costs. We exploit two properties specific to empirical risk minimization problems to accelerate Newton's method, namely, subsampling training data and increasing strong convexity through regularization. We propose a novel continuation method, where we define a family of objectives over increasing sample sizes and with decreasing regularization strength. Solutions on this path are tracked ","authors_text":"Aurelien Lucchi, Hadi Daneshmand, Thomas Hofmann","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T23:46:58Z","title":"DynaNewton - Accelerating Newton's Method for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06561","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":"sha256:5481750dc00e06d88f03ebbb7cba417711b4ca40d139fa8a8f58bd4014cc5c8d","target":"record","created_at":"2026-05-18T01:14:11Z","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":"ae5e64c1bef0e65e1d3113c72f9aabea3e0bc2d78018af4f1b9346285fe15eda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-20T23:46:58Z","title_canon_sha256":"e2a2e9478a54ef0ccdc0860c80d4781d78539da93058b2ac2a5321db1dc24650"},"schema_version":"1.0","source":{"id":"1605.06561","kind":"arxiv","version":1}},"canonical_sha256":"39fbbe5080d2a39f6359ff8a8267b277137517995cb2785f6623e00013fc836d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39fbbe5080d2a39f6359ff8a8267b277137517995cb2785f6623e00013fc836d","first_computed_at":"2026-05-18T01:14:11.874398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:11.874398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qxZYXaJCtkeG4AbuZroBZBJTrQ8bKr8pcsaOdqhS5YfAzzh2NEfRCWu/kxUL/s1Ru2hT5ZZW57VhA4U5EGUnBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:11.874889Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.06561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5481750dc00e06d88f03ebbb7cba417711b4ca40d139fa8a8f58bd4014cc5c8d","sha256:d482558d47ac885180a22dee61cdee1cd47a6c96cadf0ea69f02224248f9d33a"],"state_sha256":"178232dc2d26d68467cc6460505899211a0acfafcce2df763689a2eb43d4438f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VuaBy65GxPpURKhYxXenYqSNjVDPzkuA2D2Rgint65ugkt4LmvoMAUVcG9D8191K9Qi0pgt6KniwvlULjuiLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T00:36:20.551038Z","bundle_sha256":"d799004da74c1b5bb7957e418a975b248a564ef7291366ce2e6c20e743383ca1"}}