{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LTM75RXSVRNBORRCC7DUHKYHGN","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":"b170b073965a2aa59629253a66a6a410049af65e787b79d081f27e9d779379e0","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T22:12:31Z","title_canon_sha256":"8115fa6a4c4aefafc565ff6df0796ff40f08291b95ed8562f02c4bb9a849a5ae"},"schema_version":"1.0","source":{"id":"2307.14528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14528","created_at":"2026-07-05T06:35:14Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14528v1","created_at":"2026-07-05T06:35:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14528","created_at":"2026-07-05T06:35:14Z"},{"alias_kind":"pith_short_12","alias_value":"LTM75RXSVRNB","created_at":"2026-07-05T06:35:14Z"},{"alias_kind":"pith_short_16","alias_value":"LTM75RXSVRNBORRC","created_at":"2026-07-05T06:35:14Z"},{"alias_kind":"pith_short_8","alias_value":"LTM75RXS","created_at":"2026-07-05T06:35:14Z"}],"graph_snapshots":[{"event_id":"sha256:e802fbb0ddf87a76927bc3eb861c2d0933940e038a45cd011ee16c0b52a14e6f","target":"graph","created_at":"2026-07-05T06:35:14Z","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/2307.14528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Here we develop variants of SGD (stochastic gradient descent) with an adaptive step size that make use of the sampled loss values. In particular, we focus on solving a finite sum-of-terms problem, also known as empirical risk minimization. We first detail an idealized adaptive method called $\\texttt{SPS}_+$ that makes use of the sampled loss values and assumes knowledge of the sampled loss at optimality. This $\\texttt{SPS}_+$ is a minor modification of the SPS (Stochastic Polyak Stepsize) method, where the step size is enforced to be positive. We then show that $\\texttt{SPS}_+$ achieves the be","authors_text":"Fabian Schaipp, Guillaume Garrigos, Robert M. Gower","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T22:12:31Z","title":"Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14528","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":"sha256:97aaf4d041f62b457e28324020c70e4acd0ffcd7d6d39e46e9df2b7fc09a29d2","target":"record","created_at":"2026-07-05T06:35:14Z","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":"b170b073965a2aa59629253a66a6a410049af65e787b79d081f27e9d779379e0","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T22:12:31Z","title_canon_sha256":"8115fa6a4c4aefafc565ff6df0796ff40f08291b95ed8562f02c4bb9a849a5ae"},"schema_version":"1.0","source":{"id":"2307.14528","kind":"arxiv","version":1}},"canonical_sha256":"5cd9fec6f2ac5a17462217c743ab073359e6e4492b81b96060902086c343f52a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cd9fec6f2ac5a17462217c743ab073359e6e4492b81b96060902086c343f52a","first_computed_at":"2026-07-05T06:35:14.357900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:14.357900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QykGWtt9poydMl/VQ9MQk0MjUpfOw4VHVKL296jY/wLRQNgQt5lDRTuno89jGrYCWI6nuvbMlhYTGkXd3NL3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:14.358310Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97aaf4d041f62b457e28324020c70e4acd0ffcd7d6d39e46e9df2b7fc09a29d2","sha256:e802fbb0ddf87a76927bc3eb861c2d0933940e038a45cd011ee16c0b52a14e6f"],"state_sha256":"5c3661bdaba6af4de00e8d04d1fc6997b104bd105d45d56faf6dd26e31de26a2"}