{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SZMJ446VHFF4X24FHI7HNG23RG","short_pith_number":"pith:SZMJ446V","canonical_record":{"source":{"id":"1903.08688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-20T18:33:11Z","cross_cats_sorted":[],"title_canon_sha256":"6af506d9e384a51cc960e664226743d81eac518a21918535ef431174f3d14cc9","abstract_canon_sha256":"429a17cf5a4c4ff1b54f4b5629c7c775ff05d64e6609e5a5df560c158d62d501"},"schema_version":"1.0"},"canonical_sha256":"96589e73d5394bcbeb853a3e769b5b89ba7dbd2af3b8f9165fd22a07290a5f22","source":{"kind":"arxiv","id":"1903.08688","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.08688","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"1903.08688v2","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08688","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"SZMJ446VHFF4","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SZMJ446VHFF4X24F","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SZMJ446V","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SZMJ446VHFF4X24FHI7HNG23RG","target":"record","payload":{"canonical_record":{"source":{"id":"1903.08688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-20T18:33:11Z","cross_cats_sorted":[],"title_canon_sha256":"6af506d9e384a51cc960e664226743d81eac518a21918535ef431174f3d14cc9","abstract_canon_sha256":"429a17cf5a4c4ff1b54f4b5629c7c775ff05d64e6609e5a5df560c158d62d501"},"schema_version":"1.0"},"canonical_sha256":"96589e73d5394bcbeb853a3e769b5b89ba7dbd2af3b8f9165fd22a07290a5f22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:49.071537Z","signature_b64":"wlTYD42AvFZPzb1aYgHRJz5eE6npi0hiYr2VOchqCUq2yKjSN07ETdd0rchRFlHDRgGBsF4nzfGG2DLdtZQ6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96589e73d5394bcbeb853a3e769b5b89ba7dbd2af3b8f9165fd22a07290a5f22","last_reissued_at":"2026-05-17T23:40:49.070787Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:49.070787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.08688","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0RBf6gX9zpkInhA8vLyonNiGNgegdAfL0gK/Q0iruoMxNj7wZwnYhD1vCKOhvdgTdVJ2XqN8KH1CjySwiFEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T22:27:32.377063Z"},"content_sha256":"b8e271eca2ad96e18e96440bba59faa3086669281114ee3aa460ff1dfec8d677","schema_version":"1.0","event_id":"sha256:b8e271eca2ad96e18e96440bba59faa3086669281114ee3aa460ff1dfec8d677"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SZMJ446VHFF4X24FHI7HNG23RG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Gradient Descent with Polyak's Learning Rate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Adam M. Oberman, Mariana Prazeres","submitted_at":"2019-03-20T18:33:11Z","abstract_excerpt":"Stochastic gradient descent (SGD) for strongly convex functions converges at the rate $\\bO(1/k)$. However, achieving good results in practice requires tuning the parameters (for example the learning rate) of the algorithm. In this paper we propose a generalization of the Polyak step size, used for subgradient methods, to Stochastic gradient descent. We prove a non-asymptotic convergence at the rate $\\bO(1/k)$ with a rate constant which can be better than the corresponding rate constant for optimally scheduled SGD. We demonstrate that the method is effective in practice, and on convex optimizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08688","kind":"arxiv","version":2},"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":"2026-05-17T23:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MdT/1gHRGWT8mxsQO5XpmTdt4zA/dIE1i5v/iNsDz6ZEvKUyLdPcc7DFDUlKTifOnHzvygJCFDlJGbJg/KdxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T22:27:32.377422Z"},"content_sha256":"d3f74b3f13b30da816d189d952ada6efa94ba0a5bb1d5485d645ca7b65af6f74","schema_version":"1.0","event_id":"sha256:d3f74b3f13b30da816d189d952ada6efa94ba0a5bb1d5485d645ca7b65af6f74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZMJ446VHFF4X24FHI7HNG23RG/bundle.json","state_url":"https://pith.science/pith/SZMJ446VHFF4X24FHI7HNG23RG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZMJ446VHFF4X24FHI7HNG23RG/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":"2026-06-21T22:27:32Z","links":{"resolver":"https://pith.science/pith/SZMJ446VHFF4X24FHI7HNG23RG","bundle":"https://pith.science/pith/SZMJ446VHFF4X24FHI7HNG23RG/bundle.json","state":"https://pith.science/pith/SZMJ446VHFF4X24FHI7HNG23RG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZMJ446VHFF4X24FHI7HNG23RG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SZMJ446VHFF4X24FHI7HNG23RG","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":"429a17cf5a4c4ff1b54f4b5629c7c775ff05d64e6609e5a5df560c158d62d501","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-20T18:33:11Z","title_canon_sha256":"6af506d9e384a51cc960e664226743d81eac518a21918535ef431174f3d14cc9"},"schema_version":"1.0","source":{"id":"1903.08688","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.08688","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"1903.08688v2","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08688","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"SZMJ446VHFF4","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SZMJ446VHFF4X24F","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SZMJ446V","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:d3f74b3f13b30da816d189d952ada6efa94ba0a5bb1d5485d645ca7b65af6f74","target":"graph","created_at":"2026-05-17T23:40:49Z","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":"Stochastic gradient descent (SGD) for strongly convex functions converges at the rate $\\bO(1/k)$. However, achieving good results in practice requires tuning the parameters (for example the learning rate) of the algorithm. In this paper we propose a generalization of the Polyak step size, used for subgradient methods, to Stochastic gradient descent. We prove a non-asymptotic convergence at the rate $\\bO(1/k)$ with a rate constant which can be better than the corresponding rate constant for optimally scheduled SGD. We demonstrate that the method is effective in practice, and on convex optimizat","authors_text":"Adam M. Oberman, Mariana Prazeres","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-20T18:33:11Z","title":"Stochastic Gradient Descent with Polyak's Learning Rate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08688","kind":"arxiv","version":2},"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:b8e271eca2ad96e18e96440bba59faa3086669281114ee3aa460ff1dfec8d677","target":"record","created_at":"2026-05-17T23:40:49Z","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":"429a17cf5a4c4ff1b54f4b5629c7c775ff05d64e6609e5a5df560c158d62d501","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2019-03-20T18:33:11Z","title_canon_sha256":"6af506d9e384a51cc960e664226743d81eac518a21918535ef431174f3d14cc9"},"schema_version":"1.0","source":{"id":"1903.08688","kind":"arxiv","version":2}},"canonical_sha256":"96589e73d5394bcbeb853a3e769b5b89ba7dbd2af3b8f9165fd22a07290a5f22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96589e73d5394bcbeb853a3e769b5b89ba7dbd2af3b8f9165fd22a07290a5f22","first_computed_at":"2026-05-17T23:40:49.070787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:49.070787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wlTYD42AvFZPzb1aYgHRJz5eE6npi0hiYr2VOchqCUq2yKjSN07ETdd0rchRFlHDRgGBsF4nzfGG2DLdtZQ6BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:49.071537Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.08688","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8e271eca2ad96e18e96440bba59faa3086669281114ee3aa460ff1dfec8d677","sha256:d3f74b3f13b30da816d189d952ada6efa94ba0a5bb1d5485d645ca7b65af6f74"],"state_sha256":"c863d1010edacd3745ad7a20f55218b094cf6b5711432868119ce0aaf875c677"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mkqZm/IGWfXFFZEdAV/foPv5GSrAM9FciGxe+dCMKUxwKkqu+BJgXM7L2SS0HzfRaqfqB0tG4MEhx0jggSFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-21T22:27:32.379357Z","bundle_sha256":"1531bf105c013e963f51ee11444a0fc4bb25fd28915171135ded2d885dc5058e"}}