{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:I7XD3JVMAYKMF2KJUUUA25ULTD","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":"c8cecb97883aa167bea776a6f8472957c10af0ca7844f630f0bd7f4cb5cc6a35","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-15T21:04:11Z","title_canon_sha256":"e3fd0912a928a40be8e8f1c08593027b3cfe2040f68782dd7fe71d662094f20b"},"schema_version":"1.0","source":{"id":"1910.07056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.07056","created_at":"2026-07-05T00:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"1910.07056v1","created_at":"2026-07-05T00:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07056","created_at":"2026-07-05T00:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"I7XD3JVMAYKM","created_at":"2026-07-05T00:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"I7XD3JVMAYKMF2KJ","created_at":"2026-07-05T00:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"I7XD3JVM","created_at":"2026-07-05T00:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:da56ac9e5b16dc0f0b77101c83b3354d417d2507c6333b912777ef5517291f51","target":"graph","created_at":"2026-07-05T00:12:32Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.07056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variable metric proximal gradient (VM-PG) is a widely used class of convex optimization method. Lately, there has been a lot of research on the theoretical guarantees of VM-PG with different metric selections. However, most such metric selections are dependent on (an expensive) Hessian, or limited to scalar stepsizes like the Barzilai-Borwein (BB) stepsize with lots of safeguarding. Instead, in this paper we propose an adaptive metric selection strategy called the diagonal Barzilai-Borwein (BB) stepsize. The proposed diagonal selection better captures the local geometry of the problem while ke","authors_text":"Mohak Shah, Sauptik Dhar, Stephen Boyd, Youngsuk Park","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-15T21:04:11Z","title":"Variable Metric Proximal Gradient Method with Diagonal Barzilai-Borwein Stepsize"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07056","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":"sha256:317d43342ea367d85d4cc10d6440e13102c3fa79a168066a1a7cda759e5f599f","target":"record","created_at":"2026-07-05T00:12:32Z","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":"c8cecb97883aa167bea776a6f8472957c10af0ca7844f630f0bd7f4cb5cc6a35","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-10-15T21:04:11Z","title_canon_sha256":"e3fd0912a928a40be8e8f1c08593027b3cfe2040f68782dd7fe71d662094f20b"},"schema_version":"1.0","source":{"id":"1910.07056","kind":"arxiv","version":1}},"canonical_sha256":"47ee3da6ac0614c2e949a5280d768b98ef12f02ff0fbed5a22d5b765543ed487","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47ee3da6ac0614c2e949a5280d768b98ef12f02ff0fbed5a22d5b765543ed487","first_computed_at":"2026-07-05T00:12:32.457746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:12:32.457746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EJl2AP6IH+nrSPVD7qgOFG+6VicH3qKmLocGAFevJ/+5Mbval+WxE/8z5h8ptR6ydJ3pXnG9SlH6+fS2ScTYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:12:32.458087Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.07056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:317d43342ea367d85d4cc10d6440e13102c3fa79a168066a1a7cda759e5f599f","sha256:da56ac9e5b16dc0f0b77101c83b3354d417d2507c6333b912777ef5517291f51"],"state_sha256":"182081ceb9b1dcf9075c57aade94b9cc714bcf5a133a2cc547b511aa3f738754"}