{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6Z4CBORE2KYDLIZXJ7UAK4TNA5","short_pith_number":"pith:6Z4CBORE","schema_version":"1.0","canonical_sha256":"f67820ba24d2b035a3374fe805726d07674a16fa43a839480d1ac81bd32b7786","source":{"kind":"arxiv","id":"2002.00155","version":1},"attestation_state":"computed","paper":{"title":"Deep synthesis regularization of inverse problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Daniel Obmann, Johannes Schwab, Markus Haltmeier","submitted_at":"2020-02-01T06:50:42Z","abstract_excerpt":"Recently, a large number of efficient deep learning methods for solving inverse problems have been developed and show outstanding numerical performance. For these deep learning methods, however, a solid theoretical foundation in the form of reconstruction guarantees is missing. In contrast, for classical reconstruction methods, such as convex variational and frame-based regularization, theoretical convergence and convergence rate results are well established. In this paper, we introduce deep synthesis regularization (DESYRE) using neural networks as nonlinear synthesis operator bridging the ga"},"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":"2002.00155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2020-02-01T06:50:42Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"4192a2002c1fbf476a10cc5fec34db263894d4d33bb83150732b8e1d39d35c2d","abstract_canon_sha256":"995ffacc11df57921f3e33d70fc4aaa14474754235cc79ad7988d009fe3bd894"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:52.197177Z","signature_b64":"DLgYyClxvFPmpTQODIORIK/1E83x4rF5HD5Vw6r1h3UGl9un23d5hEx79QtmFOKIs0Z8h6PZUKSk4fymT0bZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f67820ba24d2b035a3374fe805726d07674a16fa43a839480d1ac81bd32b7786","last_reissued_at":"2026-07-05T00:37:52.196795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:52.196795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep synthesis regularization of inverse problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Daniel Obmann, Johannes Schwab, Markus Haltmeier","submitted_at":"2020-02-01T06:50:42Z","abstract_excerpt":"Recently, a large number of efficient deep learning methods for solving inverse problems have been developed and show outstanding numerical performance. For these deep learning methods, however, a solid theoretical foundation in the form of reconstruction guarantees is missing. In contrast, for classical reconstruction methods, such as convex variational and frame-based regularization, theoretical convergence and convergence rate results are well established. In this paper, we introduce deep synthesis regularization (DESYRE) using neural networks as nonlinear synthesis operator bridging the ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.00155","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/2002.00155/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":"2002.00155","created_at":"2026-07-05T00:37:52.196849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.00155v1","created_at":"2026-07-05T00:37:52.196849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.00155","created_at":"2026-07-05T00:37:52.196849+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Z4CBORE2KYD","created_at":"2026-07-05T00:37:52.196849+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Z4CBORE2KYDLIZX","created_at":"2026-07-05T00:37:52.196849+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Z4CBORE","created_at":"2026-07-05T00:37:52.196849+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23106","citing_title":"Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5","json":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5.json","graph_json":"https://pith.science/api/pith-number/6Z4CBORE2KYDLIZXJ7UAK4TNA5/graph.json","events_json":"https://pith.science/api/pith-number/6Z4CBORE2KYDLIZXJ7UAK4TNA5/events.json","paper":"https://pith.science/paper/6Z4CBORE"},"agent_actions":{"view_html":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5","download_json":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5.json","view_paper":"https://pith.science/paper/6Z4CBORE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.00155&json=true","fetch_graph":"https://pith.science/api/pith-number/6Z4CBORE2KYDLIZXJ7UAK4TNA5/graph.json","fetch_events":"https://pith.science/api/pith-number/6Z4CBORE2KYDLIZXJ7UAK4TNA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5/action/storage_attestation","attest_author":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5/action/author_attestation","sign_citation":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5/action/citation_signature","submit_replication":"https://pith.science/pith/6Z4CBORE2KYDLIZXJ7UAK4TNA5/action/replication_record"}},"created_at":"2026-07-05T00:37:52.196849+00:00","updated_at":"2026-07-05T00:37:52.196849+00:00"}