{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QDPWWORMBJRJMS5OQQJUHGW7HE","short_pith_number":"pith:QDPWWORM","schema_version":"1.0","canonical_sha256":"80df6b3a2c0a62964bae8413439adf393e4317fd01828b69749da11c12e9f4e0","source":{"kind":"arxiv","id":"2008.07281","version":1},"attestation_state":"computed","paper":{"title":"On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP","stat.ML"],"primary_cat":"eess.AS","authors_text":"Chin-Hui Lee, Jun Du, Jun Qi, Sabato Marco Siniscalchi, Xiaoli Ma","submitted_at":"2020-08-12T22:41:26Z","abstract_excerpt":"In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for the deep neural network (DNN) based vector-to-vector regression. The goal of this work is two-fold: (i) presenting performance bounds of MAE, and (ii) demonstrating new properties of MAE that make it more appropriate than mean squared error (MSE) as a loss function for DNN based vector-to-vector regression. First, we show that a generalized upper-bound for DNN-based vector- to-vector regression can be ensured by leveraging the known Lipschitz continuity property of MAE. Next, we derive a new generalize"},"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":"2008.07281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-12T22:41:26Z","cross_cats_sorted":["cs.LG","cs.SD","eess.SP","stat.ML"],"title_canon_sha256":"f22d46a5b50f54dfee2bac6100374f403cb7a66cd03297d224f4181b6c035153","abstract_canon_sha256":"1151e81c28c5a7cfaf9c9387f2ff50ac4ee34d149fa034a9fb1d9abca3fd43db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:38.275066Z","signature_b64":"n7EJInESqTqm/o6ZagHWLlb9MsrLD2BckKCe05EnKiM6fJnqdNCRwihtF4WMqHUxFkb1HXFdv4u7FqwqfINEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80df6b3a2c0a62964bae8413439adf393e4317fd01828b69749da11c12e9f4e0","last_reissued_at":"2026-07-05T01:27:38.274620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:38.274620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.SP","stat.ML"],"primary_cat":"eess.AS","authors_text":"Chin-Hui Lee, Jun Du, Jun Qi, Sabato Marco Siniscalchi, Xiaoli Ma","submitted_at":"2020-08-12T22:41:26Z","abstract_excerpt":"In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for the deep neural network (DNN) based vector-to-vector regression. The goal of this work is two-fold: (i) presenting performance bounds of MAE, and (ii) demonstrating new properties of MAE that make it more appropriate than mean squared error (MSE) as a loss function for DNN based vector-to-vector regression. First, we show that a generalized upper-bound for DNN-based vector- to-vector regression can be ensured by leveraging the known Lipschitz continuity property of MAE. Next, we derive a new generalize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07281","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/2008.07281/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":"2008.07281","created_at":"2026-07-05T01:27:38.274672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.07281v1","created_at":"2026-07-05T01:27:38.274672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07281","created_at":"2026-07-05T01:27:38.274672+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDPWWORMBJRJ","created_at":"2026-07-05T01:27:38.274672+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDPWWORMBJRJMS5O","created_at":"2026-07-05T01:27:38.274672+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDPWWORM","created_at":"2026-07-05T01:27:38.274672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06839","citing_title":"ToonOut: Fine-tuned Background-Removal for Anime Characters","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE","json":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE.json","graph_json":"https://pith.science/api/pith-number/QDPWWORMBJRJMS5OQQJUHGW7HE/graph.json","events_json":"https://pith.science/api/pith-number/QDPWWORMBJRJMS5OQQJUHGW7HE/events.json","paper":"https://pith.science/paper/QDPWWORM"},"agent_actions":{"view_html":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE","download_json":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE.json","view_paper":"https://pith.science/paper/QDPWWORM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.07281&json=true","fetch_graph":"https://pith.science/api/pith-number/QDPWWORMBJRJMS5OQQJUHGW7HE/graph.json","fetch_events":"https://pith.science/api/pith-number/QDPWWORMBJRJMS5OQQJUHGW7HE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE/action/storage_attestation","attest_author":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE/action/author_attestation","sign_citation":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE/action/citation_signature","submit_replication":"https://pith.science/pith/QDPWWORMBJRJMS5OQQJUHGW7HE/action/replication_record"}},"created_at":"2026-07-05T01:27:38.274672+00:00","updated_at":"2026-07-05T01:27:38.274672+00:00"}