{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3MHQRYTVWDABLGI3EVWKXDEJ2X","short_pith_number":"pith:3MHQRYTV","schema_version":"1.0","canonical_sha256":"db0f08e275b0c015991b256cab8c89d5d7ed458c736e6fce3e7080c8a9927b82","source":{"kind":"arxiv","id":"2211.11489","version":1},"attestation_state":"computed","paper":{"title":"Efficient Generalization Improvement Guided by Random Weight Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kun Fang, Ming Yang, Tao Li, Weihao Yan, Xiaolin Huang, Yingwen Wu, Zehao Lei","submitted_at":"2022-11-21T14:24:34Z","abstract_excerpt":"To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability. Recently, sharpness-aware minimization (SAM) establishes a generic scheme for generalization improvements by minimizing the sharpness measure within a small neighborhood and achieves state-of-the-art performance. However, SAM requires two consecutive gradient evaluations for solving the min-max problem and inevitably doubles the training time. In this paper, we resort to filter-wise random weight perturbations (RWP) to decouple the "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.11489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T14:24:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9da03d3b9a0697be6765c48f7c138c5d2dfe86fb1dd5a5551e44d06625829eda","abstract_canon_sha256":"370ba30682d13409b6817e8c3bd3404eca167e9491750eaeb96b760c300f5949"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:54.133932Z","signature_b64":"BJE76gDhojewSEB6cCFpAjXB/ZDIsx8KnYzamQG3VUHf6yRl88KLrqSbCnVlC9ZK0Y2QJORdU22x2sXhoq5SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db0f08e275b0c015991b256cab8c89d5d7ed458c736e6fce3e7080c8a9927b82","last_reissued_at":"2026-07-05T05:17:54.133593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:54.133593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Generalization Improvement Guided by Random Weight Perturbation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kun Fang, Ming Yang, Tao Li, Weihao Yan, Xiaolin Huang, Yingwen Wu, Zehao Lei","submitted_at":"2022-11-21T14:24:34Z","abstract_excerpt":"To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability. Recently, sharpness-aware minimization (SAM) establishes a generic scheme for generalization improvements by minimizing the sharpness measure within a small neighborhood and achieves state-of-the-art performance. However, SAM requires two consecutive gradient evaluations for solving the min-max problem and inevitably doubles the training time. In this paper, we resort to filter-wise random weight perturbations (RWP) to decouple the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11489","kind":"arxiv","version":1},"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/2211.11489/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.11489","created_at":"2026-07-05T05:17:54.133649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11489v1","created_at":"2026-07-05T05:17:54.133649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11489","created_at":"2026-07-05T05:17:54.133649+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MHQRYTVWDAB","created_at":"2026-07-05T05:17:54.133649+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MHQRYTVWDABLGI3","created_at":"2026-07-05T05:17:54.133649+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MHQRYTV","created_at":"2026-07-05T05:17:54.133649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00885","citing_title":"Improving Sparse-View 3DGS Generalization via Flat Minima Optimization","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X","json":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X.json","graph_json":"https://pith.science/api/pith-number/3MHQRYTVWDABLGI3EVWKXDEJ2X/graph.json","events_json":"https://pith.science/api/pith-number/3MHQRYTVWDABLGI3EVWKXDEJ2X/events.json","paper":"https://pith.science/paper/3MHQRYTV"},"agent_actions":{"view_html":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X","download_json":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X.json","view_paper":"https://pith.science/paper/3MHQRYTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11489&json=true","fetch_graph":"https://pith.science/api/pith-number/3MHQRYTVWDABLGI3EVWKXDEJ2X/graph.json","fetch_events":"https://pith.science/api/pith-number/3MHQRYTVWDABLGI3EVWKXDEJ2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X/action/storage_attestation","attest_author":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X/action/author_attestation","sign_citation":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X/action/citation_signature","submit_replication":"https://pith.science/pith/3MHQRYTVWDABLGI3EVWKXDEJ2X/action/replication_record"}},"created_at":"2026-07-05T05:17:54.133649+00:00","updated_at":"2026-07-05T05:17:54.133649+00:00"}