{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ACWDYRHMYBGD3Q742ZLESDELZK","short_pith_number":"pith:ACWDYRHM","canonical_record":{"source":{"id":"2310.04614","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-06T22:19:07Z","cross_cats_sorted":[],"title_canon_sha256":"94ad17e38712058673e596d208d9459b92f955d97d02d42a9a457e817d8d5c88","abstract_canon_sha256":"b7dd9d59038db0e02f022f09f98120c4ae4cae10131e15e9345352206623eef1"},"schema_version":"1.0"},"canonical_sha256":"00ac3c44ecc04c3dc3fcd656490c8bcaab32b7a840739afd5409f7f3810b9284","source":{"kind":"arxiv","id":"2310.04614","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04614","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04614v3","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04614","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"ACWDYRHMYBGD","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"ACWDYRHMYBGD3Q74","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"ACWDYRHM","created_at":"2026-07-05T09:18:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ACWDYRHMYBGD3Q742ZLESDELZK","target":"record","payload":{"canonical_record":{"source":{"id":"2310.04614","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-06T22:19:07Z","cross_cats_sorted":[],"title_canon_sha256":"94ad17e38712058673e596d208d9459b92f955d97d02d42a9a457e817d8d5c88","abstract_canon_sha256":"b7dd9d59038db0e02f022f09f98120c4ae4cae10131e15e9345352206623eef1"},"schema_version":"1.0"},"canonical_sha256":"00ac3c44ecc04c3dc3fcd656490c8bcaab32b7a840739afd5409f7f3810b9284","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:20.886217Z","signature_b64":"/FHD4jBpP6x5v3p4ZURagsmY18Fd8C8jicQfcr+O06tsWdaCmjWTJxLMr6GomVzThVt1tFl4knDg5uq6HZCCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00ac3c44ecc04c3dc3fcd656490c8bcaab32b7a840739afd5409f7f3810b9284","last_reissued_at":"2026-07-05T09:18:20.885811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:20.885811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.04614","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YrAHrrOOZUXII6qWahsLM+RMN4S0WSUTIGBquwldBNaBb+O49NwlQC6hbQGlqaxsU+h5eta9hSlYXDQx+tgjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:31:51.306095Z"},"content_sha256":"b5f560a405399b53237cc9d15d783013755e2283e90446ca01a236de81be92da","schema_version":"1.0","event_id":"sha256:b5f560a405399b53237cc9d15d783013755e2283e90446ca01a236de81be92da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ACWDYRHMYBGD3Q742ZLESDELZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Avetik Karagulyan, Hanmin Li, Peter Richt\\'arik","submitted_at":"2023-10-06T22:19:07Z","abstract_excerpt":"Matrix-stepsized gradient descent algorithms have been shown to have superior performance in non-convex optimization problems compared to their scalar counterparts. The det-CGD algorithm, as introduced by Li et al. (2023), leverages matrix stepsizes to perform compressed gradient descent for non-convex objectives and matrix-smooth problems in a federated manner. The authors establish the algorithm's convergence to a neighborhood of a weighted stationarity point under a convex condition for the symmetric and positive-definite matrix stepsize. In this paper, we propose two variance-reduced versi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04614","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.04614/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T09:18:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjMZbtaRYFeuc5UTmYkwg7Lkaxh9izI1qlpUAmY65DgVUHW5+sGRSmyLzlVDbnocrDPX016O8D9pevelD2euCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:31:51.306582Z"},"content_sha256":"ef6fd6aece8b21bd9459cc4ad2fafc9f98c8930f70ca525035530a5620b31611","schema_version":"1.0","event_id":"sha256:ef6fd6aece8b21bd9459cc4ad2fafc9f98c8930f70ca525035530a5620b31611"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACWDYRHMYBGD3Q742ZLESDELZK/bundle.json","state_url":"https://pith.science/pith/ACWDYRHMYBGD3Q742ZLESDELZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACWDYRHMYBGD3Q742ZLESDELZK/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":"2026-08-04T22:31:51Z","links":{"resolver":"https://pith.science/pith/ACWDYRHMYBGD3Q742ZLESDELZK","bundle":"https://pith.science/pith/ACWDYRHMYBGD3Q742ZLESDELZK/bundle.json","state":"https://pith.science/pith/ACWDYRHMYBGD3Q742ZLESDELZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACWDYRHMYBGD3Q742ZLESDELZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ACWDYRHMYBGD3Q742ZLESDELZK","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":"b7dd9d59038db0e02f022f09f98120c4ae4cae10131e15e9345352206623eef1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-06T22:19:07Z","title_canon_sha256":"94ad17e38712058673e596d208d9459b92f955d97d02d42a9a457e817d8d5c88"},"schema_version":"1.0","source":{"id":"2310.04614","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04614","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04614v3","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04614","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"pith_short_12","alias_value":"ACWDYRHMYBGD","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"pith_short_16","alias_value":"ACWDYRHMYBGD3Q74","created_at":"2026-07-05T09:18:20Z"},{"alias_kind":"pith_short_8","alias_value":"ACWDYRHM","created_at":"2026-07-05T09:18:20Z"}],"graph_snapshots":[{"event_id":"sha256:ef6fd6aece8b21bd9459cc4ad2fafc9f98c8930f70ca525035530a5620b31611","target":"graph","created_at":"2026-07-05T09:18:20Z","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/2310.04614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Matrix-stepsized gradient descent algorithms have been shown to have superior performance in non-convex optimization problems compared to their scalar counterparts. The det-CGD algorithm, as introduced by Li et al. (2023), leverages matrix stepsizes to perform compressed gradient descent for non-convex objectives and matrix-smooth problems in a federated manner. The authors establish the algorithm's convergence to a neighborhood of a weighted stationarity point under a convex condition for the symmetric and positive-definite matrix stepsize. In this paper, we propose two variance-reduced versi","authors_text":"Avetik Karagulyan, Hanmin Li, Peter Richt\\'arik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-06T22:19:07Z","title":"Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04614","kind":"arxiv","version":3},"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:b5f560a405399b53237cc9d15d783013755e2283e90446ca01a236de81be92da","target":"record","created_at":"2026-07-05T09:18:20Z","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":"b7dd9d59038db0e02f022f09f98120c4ae4cae10131e15e9345352206623eef1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-10-06T22:19:07Z","title_canon_sha256":"94ad17e38712058673e596d208d9459b92f955d97d02d42a9a457e817d8d5c88"},"schema_version":"1.0","source":{"id":"2310.04614","kind":"arxiv","version":3}},"canonical_sha256":"00ac3c44ecc04c3dc3fcd656490c8bcaab32b7a840739afd5409f7f3810b9284","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00ac3c44ecc04c3dc3fcd656490c8bcaab32b7a840739afd5409f7f3810b9284","first_computed_at":"2026-07-05T09:18:20.885811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:20.885811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/FHD4jBpP6x5v3p4ZURagsmY18Fd8C8jicQfcr+O06tsWdaCmjWTJxLMr6GomVzThVt1tFl4knDg5uq6HZCCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:20.886217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04614","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5f560a405399b53237cc9d15d783013755e2283e90446ca01a236de81be92da","sha256:ef6fd6aece8b21bd9459cc4ad2fafc9f98c8930f70ca525035530a5620b31611"],"state_sha256":"6ef1b6b9a1748250472d78e3464a2f5743cf7ff809bb53c203884e9ae9f9741d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IjytFtLns5NsBD/Q8ZWdctz58rXqC9r7pLoAPzuZuZQshsmaWFMoIu/U1lN32hH4i9xMYTaNpAaNfo3jvx1xAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:31:51.310115Z","bundle_sha256":"7fa4d1c53cfebf16f2acf04de5edb44807e7880a78a97c2fb80732c989586c41"}}