{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YM6FYWZICMOWWAYKZ2VNIQBPFK","short_pith_number":"pith:YM6FYWZI","canonical_record":{"source":{"id":"1901.09068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T20:17:39Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"16e62e1a96d2d816b618bd7fca5c254e8621491e24485495233fbe2803c2953b","abstract_canon_sha256":"fb0f45073a1b1aea76037586b657f9316c5bf268a0093301b4ac6aef35160085"},"schema_version":"1.0"},"canonical_sha256":"c33c5c5b28131d6b030aceaad4402f2aa2cda6ce17c2b5afdce9bac366077476","source":{"kind":"arxiv","id":"1901.09068","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09068","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09068v2","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09068","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"YM6FYWZICMOW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YM6FYWZICMOWWAYK","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YM6FYWZI","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YM6FYWZICMOWWAYKZ2VNIQBPFK","target":"record","payload":{"canonical_record":{"source":{"id":"1901.09068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T20:17:39Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"16e62e1a96d2d816b618bd7fca5c254e8621491e24485495233fbe2803c2953b","abstract_canon_sha256":"fb0f45073a1b1aea76037586b657f9316c5bf268a0093301b4ac6aef35160085"},"schema_version":"1.0"},"canonical_sha256":"c33c5c5b28131d6b030aceaad4402f2aa2cda6ce17c2b5afdce9bac366077476","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:56.310927Z","signature_b64":"S9N3z7PzheVgluqA+xpn5P/QAdpJyuy18p9CIuXonfg2yiNXAHHePvgEe4iqrRyZJ70Do4kpO9TIiNSAfZdkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c33c5c5b28131d6b030aceaad4402f2aa2cda6ce17c2b5afdce9bac366077476","last_reissued_at":"2026-05-17T23:43:56.310185Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:56.310185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.09068","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":"2026-05-17T23:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0d/ag4Kj5itsME9Y8ZVXuUzLRPYlQNAusyITnwUbrdLuUAfPk7zySUFd9qc/EGIXKS3fcIlgZ2FmMOVvBLFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:14:30.985198Z"},"content_sha256":"123177ba8e6e977c862094c0881ccdf1ed6f7e089c266ac4a015950b0ab77f76","schema_version":"1.0","event_id":"sha256:123177ba8e6e977c862094c0881ccdf1ed6f7e089c266ac4a015950b0ab77f76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YM6FYWZICMOWWAYKZ2VNIQBPFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashok Cutkosky, Francesco Orabona, Zhenxun Zhuang","submitted_at":"2019-01-25T20:17:39Z","abstract_excerpt":"Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several years, a plethora of adaptive gradient-based algorithms have emerged to ameliorate this problem. They have proved efficient in reducing the labor of tuning in practice, but many of them lack theoretic guarantees even in the convex setting. In this paper, we propose new surrogate losses to cast the problem of learning the optimal stepsizes for the stochastic opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09068","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":"2026-05-17T23:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pa7LKJCJB9Re9T1TGmpIsMmGhzNGmC8+NzFHkAUypyvpYoTLjCfKFjxXJuUK8ovl8NW6YXuWc2MlN/NQHy8oBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:14:30.985857Z"},"content_sha256":"f0999c9969afdf5161e59386f81e955dd3630747421e877a7fff17e96ff6d015","schema_version":"1.0","event_id":"sha256:f0999c9969afdf5161e59386f81e955dd3630747421e877a7fff17e96ff6d015"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YM6FYWZICMOWWAYKZ2VNIQBPFK/bundle.json","state_url":"https://pith.science/pith/YM6FYWZICMOWWAYKZ2VNIQBPFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YM6FYWZICMOWWAYKZ2VNIQBPFK/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":"2026-05-27T05:14:30Z","links":{"resolver":"https://pith.science/pith/YM6FYWZICMOWWAYKZ2VNIQBPFK","bundle":"https://pith.science/pith/YM6FYWZICMOWWAYKZ2VNIQBPFK/bundle.json","state":"https://pith.science/pith/YM6FYWZICMOWWAYKZ2VNIQBPFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YM6FYWZICMOWWAYKZ2VNIQBPFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YM6FYWZICMOWWAYKZ2VNIQBPFK","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":"fb0f45073a1b1aea76037586b657f9316c5bf268a0093301b4ac6aef35160085","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T20:17:39Z","title_canon_sha256":"16e62e1a96d2d816b618bd7fca5c254e8621491e24485495233fbe2803c2953b"},"schema_version":"1.0","source":{"id":"1901.09068","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09068","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09068v2","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09068","created_at":"2026-05-17T23:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"YM6FYWZICMOW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YM6FYWZICMOWWAYK","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YM6FYWZI","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:f0999c9969afdf5161e59386f81e955dd3630747421e877a7fff17e96ff6d015","target":"graph","created_at":"2026-05-17T23:43:56Z","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) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several years, a plethora of adaptive gradient-based algorithms have emerged to ameliorate this problem. They have proved efficient in reducing the labor of tuning in practice, but many of them lack theoretic guarantees even in the convex setting. In this paper, we propose new surrogate losses to cast the problem of learning the optimal stepsizes for the stochastic opti","authors_text":"Ashok Cutkosky, Francesco Orabona, Zhenxun Zhuang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T20:17:39Z","title":"Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09068","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":"sha256:123177ba8e6e977c862094c0881ccdf1ed6f7e089c266ac4a015950b0ab77f76","target":"record","created_at":"2026-05-17T23:43:56Z","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":"fb0f45073a1b1aea76037586b657f9316c5bf268a0093301b4ac6aef35160085","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-25T20:17:39Z","title_canon_sha256":"16e62e1a96d2d816b618bd7fca5c254e8621491e24485495233fbe2803c2953b"},"schema_version":"1.0","source":{"id":"1901.09068","kind":"arxiv","version":2}},"canonical_sha256":"c33c5c5b28131d6b030aceaad4402f2aa2cda6ce17c2b5afdce9bac366077476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c33c5c5b28131d6b030aceaad4402f2aa2cda6ce17c2b5afdce9bac366077476","first_computed_at":"2026-05-17T23:43:56.310185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:56.310185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S9N3z7PzheVgluqA+xpn5P/QAdpJyuy18p9CIuXonfg2yiNXAHHePvgEe4iqrRyZJ70Do4kpO9TIiNSAfZdkBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:56.310927Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09068","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:123177ba8e6e977c862094c0881ccdf1ed6f7e089c266ac4a015950b0ab77f76","sha256:f0999c9969afdf5161e59386f81e955dd3630747421e877a7fff17e96ff6d015"],"state_sha256":"36b0344f7533e63113109a85a1dd9f86211aa5513aa8358edf14edb0d2b148ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8eSPv0PgTReBcBEh0nfH9Hd1Eqx041Z1TrFvYgkLcvyvotavKjG5cuElVwZG98jpd5XLX4cIdBvFFefT/b4hDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:14:30.989310Z","bundle_sha256":"4aafc5c734ee3ea6a7044222f00ac6d35181b71e804a61524178d6958a30a47e"}}