{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Z73KTHUJKLVSAAZLZXT4FR6HJJ","short_pith_number":"pith:Z73KTHUJ","canonical_record":{"source":{"id":"1909.05142","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-11T15:32:44Z","cross_cats_sorted":["cs.LG","stat.AP","stat.CO"],"title_canon_sha256":"12d735c69045600d09ac53d95e4eef3aab8f3e25c030210452110a5fda653473","abstract_canon_sha256":"2dafbc21ca9531d47784f7bdaca152bb0c417d1b6b141b79ba965b4366e2ecff"},"schema_version":"1.0"},"canonical_sha256":"cff6a99e8952eb20032bcde7c2c7c74a44492aafa46b6e938ca36ba1a4d22a8d","source":{"kind":"arxiv","id":"1909.05142","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.05142","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.05142v4","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05142","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"Z73KTHUJKLVS","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z73KTHUJKLVSAAZL","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z73KTHUJ","created_at":"2026-07-05T04:11:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Z73KTHUJKLVSAAZLZXT4FR6HJJ","target":"record","payload":{"canonical_record":{"source":{"id":"1909.05142","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-11T15:32:44Z","cross_cats_sorted":["cs.LG","stat.AP","stat.CO"],"title_canon_sha256":"12d735c69045600d09ac53d95e4eef3aab8f3e25c030210452110a5fda653473","abstract_canon_sha256":"2dafbc21ca9531d47784f7bdaca152bb0c417d1b6b141b79ba965b4366e2ecff"},"schema_version":"1.0"},"canonical_sha256":"cff6a99e8952eb20032bcde7c2c7c74a44492aafa46b6e938ca36ba1a4d22a8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:59.486820Z","signature_b64":"JW2hftQM4q480JHKOx4w+oUw3XbJ9co+XeuleBHx9mvxmhmNDb4f+oQg1Jn6Jk+21NwNSlUQkxMnDqxMgCtUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cff6a99e8952eb20032bcde7c2c7c74a44492aafa46b6e938ca36ba1a4d22a8d","last_reissued_at":"2026-07-05T04:11:59.486395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:59.486395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.05142","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ViyHV6GGVbZ+RsABkqiWUYuaYImLzSvyQq9klL2YaOMjJMIAH6yqNTCzrUEYpp3kvHFLSYceZjm9MNX+tG7QBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:51:45.339195Z"},"content_sha256":"1a8dc80360861ef2dd68d0e1bd52d113cc79a2c04e055347ceeef8dd063af330","schema_version":"1.0","event_id":"sha256:1a8dc80360861ef2dd68d0e1bd52d113cc79a2c04e055347ceeef8dd063af330"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Z73KTHUJKLVSAAZLZXT4FR6HJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularized deep learning with nonconvex penalties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.CO"],"primary_cat":"stat.ML","authors_text":"Majnu John, Sujit Vettam","submitted_at":"2019-09-11T15:32:44Z","abstract_excerpt":"Regularization methods are often employed in deep learning neural networks (DNNs) to prevent overfitting. For penalty based DNN regularization methods, convex penalties are typically considered because of their optimization guarantees. Recent theoretical work have shown that nonconvex penalties that satisfy certain regularity conditions are also guaranteed to perform well with standard optimization algorithms. In this paper, we examine new and currently existing nonconvex penalties for DNN regularization. We provide theoretical justifications for the new penalties and also assess the performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05142","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.05142/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHdl4kZBV/1XAOQjXAbEWpYEuCgD/M8/r50GkX9PDMo//CP5Ln2CpBUT7vUYWLhYPB4BVlXgg+RLan3HcLNCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:51:45.339791Z"},"content_sha256":"1e071d44982f3bf809eb1d24350a3fba41d191680835235792c52c5a80c1fcc0","schema_version":"1.0","event_id":"sha256:1e071d44982f3bf809eb1d24350a3fba41d191680835235792c52c5a80c1fcc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z73KTHUJKLVSAAZLZXT4FR6HJJ/bundle.json","state_url":"https://pith.science/pith/Z73KTHUJKLVSAAZLZXT4FR6HJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z73KTHUJKLVSAAZLZXT4FR6HJJ/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":"2026-08-15T04:51:45Z","links":{"resolver":"https://pith.science/pith/Z73KTHUJKLVSAAZLZXT4FR6HJJ","bundle":"https://pith.science/pith/Z73KTHUJKLVSAAZLZXT4FR6HJJ/bundle.json","state":"https://pith.science/pith/Z73KTHUJKLVSAAZLZXT4FR6HJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z73KTHUJKLVSAAZLZXT4FR6HJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Z73KTHUJKLVSAAZLZXT4FR6HJJ","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":"2dafbc21ca9531d47784f7bdaca152bb0c417d1b6b141b79ba965b4366e2ecff","cross_cats_sorted":["cs.LG","stat.AP","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-11T15:32:44Z","title_canon_sha256":"12d735c69045600d09ac53d95e4eef3aab8f3e25c030210452110a5fda653473"},"schema_version":"1.0","source":{"id":"1909.05142","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.05142","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"1909.05142v4","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05142","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"Z73KTHUJKLVS","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"Z73KTHUJKLVSAAZL","created_at":"2026-07-05T04:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"Z73KTHUJ","created_at":"2026-07-05T04:11:59Z"}],"graph_snapshots":[{"event_id":"sha256:1e071d44982f3bf809eb1d24350a3fba41d191680835235792c52c5a80c1fcc0","target":"graph","created_at":"2026-07-05T04:11:59Z","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/1909.05142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Regularization methods are often employed in deep learning neural networks (DNNs) to prevent overfitting. For penalty based DNN regularization methods, convex penalties are typically considered because of their optimization guarantees. Recent theoretical work have shown that nonconvex penalties that satisfy certain regularity conditions are also guaranteed to perform well with standard optimization algorithms. In this paper, we examine new and currently existing nonconvex penalties for DNN regularization. We provide theoretical justifications for the new penalties and also assess the performan","authors_text":"Majnu John, Sujit Vettam","cross_cats":["cs.LG","stat.AP","stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-11T15:32:44Z","title":"Regularized deep learning with nonconvex penalties"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05142","kind":"arxiv","version":4},"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":"sha256:1a8dc80360861ef2dd68d0e1bd52d113cc79a2c04e055347ceeef8dd063af330","target":"record","created_at":"2026-07-05T04:11:59Z","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":"2dafbc21ca9531d47784f7bdaca152bb0c417d1b6b141b79ba965b4366e2ecff","cross_cats_sorted":["cs.LG","stat.AP","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-11T15:32:44Z","title_canon_sha256":"12d735c69045600d09ac53d95e4eef3aab8f3e25c030210452110a5fda653473"},"schema_version":"1.0","source":{"id":"1909.05142","kind":"arxiv","version":4}},"canonical_sha256":"cff6a99e8952eb20032bcde7c2c7c74a44492aafa46b6e938ca36ba1a4d22a8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cff6a99e8952eb20032bcde7c2c7c74a44492aafa46b6e938ca36ba1a4d22a8d","first_computed_at":"2026-07-05T04:11:59.486395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:59.486395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JW2hftQM4q480JHKOx4w+oUw3XbJ9co+XeuleBHx9mvxmhmNDb4f+oQg1Jn6Jk+21NwNSlUQkxMnDqxMgCtUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:59.486820Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.05142","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a8dc80360861ef2dd68d0e1bd52d113cc79a2c04e055347ceeef8dd063af330","sha256:1e071d44982f3bf809eb1d24350a3fba41d191680835235792c52c5a80c1fcc0"],"state_sha256":"455edb5a114249f72fe4810af875cd7d6e15d40c6547616d57d6259a836da9da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lIdtglxZ1DN++V1BVVxKlLqPr+TMwlBrBw9ZY+yUuo6y4xHRr7SlbMNVTC098zsOZaCnGPjmW8vSkgv/9iSsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T04:51:45.343468Z","bundle_sha256":"f503e584497f6fd2cf1d04d8a2361f02a83b547fbeba790bb2e2e2dc288dfe0b"}}