{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:LF374EJ5ALRD7K5RAGK27C26ZQ","short_pith_number":"pith:LF374EJ5","canonical_record":{"source":{"id":"1212.1824","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-08T18:22:42Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"73e6f59e5c1d6bb09f05f058b6c3101495aef883200b403d97c513a810e3da67","abstract_canon_sha256":"075d7bcb25498f6ade06def53a3a5dfe56b95e6f494abb99a430940e1263beee"},"schema_version":"1.0"},"canonical_sha256":"5977fe113d02e23fabb10195af8b5ecc00d22c43753ebe14755f7831731a53e4","source":{"kind":"arxiv","id":"1212.1824","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1212.1824","created_at":"2026-05-18T03:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"1212.1824v2","created_at":"2026-05-18T03:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.1824","created_at":"2026-05-18T03:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"LF374EJ5ALRD","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"LF374EJ5ALRD7K5R","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"LF374EJ5","created_at":"2026-05-18T12:27:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:LF374EJ5ALRD7K5RAGK27C26ZQ","target":"record","payload":{"canonical_record":{"source":{"id":"1212.1824","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-08T18:22:42Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"73e6f59e5c1d6bb09f05f058b6c3101495aef883200b403d97c513a810e3da67","abstract_canon_sha256":"075d7bcb25498f6ade06def53a3a5dfe56b95e6f494abb99a430940e1263beee"},"schema_version":"1.0"},"canonical_sha256":"5977fe113d02e23fabb10195af8b5ecc00d22c43753ebe14755f7831731a53e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:37:40.558970Z","signature_b64":"5KHzAFyvpuN+WzDnPJMjJVGitMoxXaxilhhVpWZ65jFikjiluyoTnRrG+uD+LI6ObyyvhGiBT7WxWZHImtSFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5977fe113d02e23fabb10195af8b5ecc00d22c43753ebe14755f7831731a53e4","last_reissued_at":"2026-05-18T03:37:40.558466Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:37:40.558466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1212.1824","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":"2026-05-18T03:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zHD9YqLoOr2CvtD67ZrJbyHgvGeVZfA0YT0SkqMXyFswk4XS83jAN7Vg1+R4LsR3g9rv/5r1/b9HqG86ieMGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:22:43.706515Z"},"content_sha256":"652dc973be9f7c2a741de7ed45d60445a8fd716aaece088a7d2cb0fc04f3b704","schema_version":"1.0","event_id":"sha256:652dc973be9f7c2a741de7ed45d60445a8fd716aaece088a7d2cb0fc04f3b704"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:LF374EJ5ALRD7K5RAGK27C26ZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ohad Shamir, Tong Zhang","submitted_at":"2012-12-08T18:22:42Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness assumptions, which do not apply to many modern applications of SGD with non-smooth objective functions such as support vector machines. In this paper, we investigate the performance of SGD without such smoothness assumptions, as well as a running average scheme to convert the SGD iterates to a solution with optimal optimization accuracy. In this framework, we prove t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.1824","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":"2026-05-18T03:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6z0xn7PSuD2xqAqikfNMHb4xyb5bQgVW211X3s86rfeeEzeWFGeYF5/zQT8hD7TyHRujaaMem+T/R3bhKx0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:22:43.707182Z"},"content_sha256":"353eb5d8173a00e65c016e0434690f09fbffadc08eeab09b93b3f88ed74f3dae","schema_version":"1.0","event_id":"sha256:353eb5d8173a00e65c016e0434690f09fbffadc08eeab09b93b3f88ed74f3dae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LF374EJ5ALRD7K5RAGK27C26ZQ/bundle.json","state_url":"https://pith.science/pith/LF374EJ5ALRD7K5RAGK27C26ZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LF374EJ5ALRD7K5RAGK27C26ZQ/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":"2026-06-12T02:22:43Z","links":{"resolver":"https://pith.science/pith/LF374EJ5ALRD7K5RAGK27C26ZQ","bundle":"https://pith.science/pith/LF374EJ5ALRD7K5RAGK27C26ZQ/bundle.json","state":"https://pith.science/pith/LF374EJ5ALRD7K5RAGK27C26ZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LF374EJ5ALRD7K5RAGK27C26ZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:LF374EJ5ALRD7K5RAGK27C26ZQ","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":"075d7bcb25498f6ade06def53a3a5dfe56b95e6f494abb99a430940e1263beee","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-08T18:22:42Z","title_canon_sha256":"73e6f59e5c1d6bb09f05f058b6c3101495aef883200b403d97c513a810e3da67"},"schema_version":"1.0","source":{"id":"1212.1824","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1212.1824","created_at":"2026-05-18T03:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"1212.1824v2","created_at":"2026-05-18T03:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.1824","created_at":"2026-05-18T03:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"LF374EJ5ALRD","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"LF374EJ5ALRD7K5R","created_at":"2026-05-18T12:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"LF374EJ5","created_at":"2026-05-18T12:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:353eb5d8173a00e65c016e0434690f09fbffadc08eeab09b93b3f88ed74f3dae","target":"graph","created_at":"2026-05-18T03:37:40Z","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) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness assumptions, which do not apply to many modern applications of SGD with non-smooth objective functions such as support vector machines. In this paper, we investigate the performance of SGD without such smoothness assumptions, as well as a running average scheme to convert the SGD iterates to a solution with optimal optimization accuracy. In this framework, we prove t","authors_text":"Ohad Shamir, Tong Zhang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-08T18:22:42Z","title":"Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.1824","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":"sha256:652dc973be9f7c2a741de7ed45d60445a8fd716aaece088a7d2cb0fc04f3b704","target":"record","created_at":"2026-05-18T03:37:40Z","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":"075d7bcb25498f6ade06def53a3a5dfe56b95e6f494abb99a430940e1263beee","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-08T18:22:42Z","title_canon_sha256":"73e6f59e5c1d6bb09f05f058b6c3101495aef883200b403d97c513a810e3da67"},"schema_version":"1.0","source":{"id":"1212.1824","kind":"arxiv","version":2}},"canonical_sha256":"5977fe113d02e23fabb10195af8b5ecc00d22c43753ebe14755f7831731a53e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5977fe113d02e23fabb10195af8b5ecc00d22c43753ebe14755f7831731a53e4","first_computed_at":"2026-05-18T03:37:40.558466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:37:40.558466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5KHzAFyvpuN+WzDnPJMjJVGitMoxXaxilhhVpWZ65jFikjiluyoTnRrG+uD+LI6ObyyvhGiBT7WxWZHImtSFAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:37:40.558970Z","signed_message":"canonical_sha256_bytes"},"source_id":"1212.1824","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:652dc973be9f7c2a741de7ed45d60445a8fd716aaece088a7d2cb0fc04f3b704","sha256:353eb5d8173a00e65c016e0434690f09fbffadc08eeab09b93b3f88ed74f3dae"],"state_sha256":"8bed25cc391c19d6f9f35177cdfd982c6d9068d05a94ef3a07dc65f130192165"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BgcUI5UN42LnSZhbW9SW1gz64pBQuujlV3D4TlWVY4g4J+FMD+yfdpeYdEYT48CsV7ItPdlLt8xGXoKtKX2ACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T02:22:43.711077Z","bundle_sha256":"d201bd7835d7fa9d66be98e4d6a8d2762986c3a4c01b21cd45530cedeac4c4e5"}}