{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WJK4YZB3SGW6JOXCZOOTQBL7PF","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":"ca060670ac39e847d9ded0777badb81d073d50dc45601b442893e167ef215df2","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T21:24:26Z","title_canon_sha256":"c919e8c5b5caeef5c8d9de498e5cebd4d726fbdff54f557a5c65e14de240dbc1"},"schema_version":"1.0","source":{"id":"2209.15106","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15106","created_at":"2026-07-05T05:02:15Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15106v1","created_at":"2026-07-05T05:02:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15106","created_at":"2026-07-05T05:02:15Z"},{"alias_kind":"pith_short_12","alias_value":"WJK4YZB3SGW6","created_at":"2026-07-05T05:02:15Z"},{"alias_kind":"pith_short_16","alias_value":"WJK4YZB3SGW6JOXC","created_at":"2026-07-05T05:02:15Z"},{"alias_kind":"pith_short_8","alias_value":"WJK4YZB3","created_at":"2026-07-05T05:02:15Z"}],"graph_snapshots":[{"event_id":"sha256:779b67185653747cd9c418ba8b646e326d16236686f710e87b89a90272409cc7","target":"graph","created_at":"2026-07-05T05:02:15Z","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/2209.15106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of optimization of deep learning models with smooth activation functions. While there exist influential results on the problem from the ``near initialization'' perspective, we shed considerable new light on the problem. In particular, we make two key technical contributions for such models with $L$ layers, $m$ width, and $\\sigma_0^2$ initialization variance. First, for suitable $\\sigma_0^2$, we establish a $O(\\frac{\\text{poly}(L)}{\\sqrt{m}})$ upper bound on the spectral norm of the Hessian of such models, considerably sharpening prior results. Second, we introduce a new","authors_text":"Arindam Banerjee, Libin Zhu, Mikhail Belkin, Pedro Cisneros-Velarde","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T21:24:26Z","title":"Restricted Strong Convexity of Deep Learning Models with Smooth Activations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15106","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:ccc283ff4342af041a8aa77374522519ad289406c91091b85158977c7aac2b84","target":"record","created_at":"2026-07-05T05:02:15Z","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":"ca060670ac39e847d9ded0777badb81d073d50dc45601b442893e167ef215df2","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-29T21:24:26Z","title_canon_sha256":"c919e8c5b5caeef5c8d9de498e5cebd4d726fbdff54f557a5c65e14de240dbc1"},"schema_version":"1.0","source":{"id":"2209.15106","kind":"arxiv","version":1}},"canonical_sha256":"b255cc643b91ade4bae2cb9d38057f795f478b7004934a2d8cf33a89c1e63818","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b255cc643b91ade4bae2cb9d38057f795f478b7004934a2d8cf33a89c1e63818","first_computed_at":"2026-07-05T05:02:15.908939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:15.908939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C8Yx9aOp43drbbVTSXE3GpNPcFsaLw8xaQAl0FylWFOLYfQq3jE6oDLTMsV4pTi3byurhIDkURwoKwbiz+T9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:15.909349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15106","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccc283ff4342af041a8aa77374522519ad289406c91091b85158977c7aac2b84","sha256:779b67185653747cd9c418ba8b646e326d16236686f710e87b89a90272409cc7"],"state_sha256":"13fe4aaa639358dea88c8c2c7d11b7f203c2e2aebfbc3529e667334dfa1a23d9"}