{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JRLS3IQ6RLLLQTWL6VUCOMN2JP","short_pith_number":"pith:JRLS3IQ6","schema_version":"1.0","canonical_sha256":"4c572da21e8ad6b84ecbf5682731ba4bc630b9d19a5a9a079148374d015202a7","source":{"kind":"arxiv","id":"2111.11986","version":1},"attestation_state":"computed","paper":{"title":"HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Huanrui Yang, Neil Zhenqiang Gong, Xiaoxuan Yang, Yiran Chen","submitted_at":"2021-11-23T16:32:58Z","abstract_excerpt":"With the recent demand of deploying neural network models on mobile and edge devices, it is desired to improve the model's generalizability on unseen testing data, as well as enhance the model's robustness under fixed-point quantization for efficient deployment. Minimizing the training loss, however, provides few guarantees on the generalization and quantization performance. In this work, we fulfill the need of improving generalization and quantization performance simultaneously by theoretically unifying them under the framework of improving the model's robustness against bounded weight pertur"},"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":"2111.11986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-23T16:32:58Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e7cb4c155d225576e6650b0afe3478c97fe941fcc13b6664cd7cb6f4b96a6b78","abstract_canon_sha256":"0fc1348004399f25d59cf29936a54ce87d18faca7554fb46a91dba95ffb5ff45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:55.146580Z","signature_b64":"9ebKlosXFb6HH/BwfCrEIVt9A0XKXjYPDdbeS33hdO7i4WDQ1XMM2kxVoAmxbM/OllUWJyzWaqx5caFhUCwaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c572da21e8ad6b84ecbf5682731ba4bc630b9d19a5a9a079148374d015202a7","last_reissued_at":"2026-07-05T03:34:55.146099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:55.146099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HERO: Hessian-Enhanced Robust Optimization for Unifying and Improving Generalization and Quantization Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Huanrui Yang, Neil Zhenqiang Gong, Xiaoxuan Yang, Yiran Chen","submitted_at":"2021-11-23T16:32:58Z","abstract_excerpt":"With the recent demand of deploying neural network models on mobile and edge devices, it is desired to improve the model's generalizability on unseen testing data, as well as enhance the model's robustness under fixed-point quantization for efficient deployment. Minimizing the training loss, however, provides few guarantees on the generalization and quantization performance. In this work, we fulfill the need of improving generalization and quantization performance simultaneously by theoretically unifying them under the framework of improving the model's robustness against bounded weight pertur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11986","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/2111.11986/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":"2111.11986","created_at":"2026-07-05T03:34:55.146158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11986v1","created_at":"2026-07-05T03:34:55.146158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11986","created_at":"2026-07-05T03:34:55.146158+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRLS3IQ6RLLL","created_at":"2026-07-05T03:34:55.146158+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRLS3IQ6RLLLQTWL","created_at":"2026-07-05T03:34:55.146158+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRLS3IQ6","created_at":"2026-07-05T03:34:55.146158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15167","citing_title":"When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP","json":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP.json","graph_json":"https://pith.science/api/pith-number/JRLS3IQ6RLLLQTWL6VUCOMN2JP/graph.json","events_json":"https://pith.science/api/pith-number/JRLS3IQ6RLLLQTWL6VUCOMN2JP/events.json","paper":"https://pith.science/paper/JRLS3IQ6"},"agent_actions":{"view_html":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP","download_json":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP.json","view_paper":"https://pith.science/paper/JRLS3IQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11986&json=true","fetch_graph":"https://pith.science/api/pith-number/JRLS3IQ6RLLLQTWL6VUCOMN2JP/graph.json","fetch_events":"https://pith.science/api/pith-number/JRLS3IQ6RLLLQTWL6VUCOMN2JP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP/action/storage_attestation","attest_author":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP/action/author_attestation","sign_citation":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP/action/citation_signature","submit_replication":"https://pith.science/pith/JRLS3IQ6RLLLQTWL6VUCOMN2JP/action/replication_record"}},"created_at":"2026-07-05T03:34:55.146158+00:00","updated_at":"2026-07-05T03:34:55.146158+00:00"}