{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:APR7767ZTW2IZLJWLYTSHRUOSE","short_pith_number":"pith:APR7767Z","schema_version":"1.0","canonical_sha256":"03e3fffbf99db48cad365e2723c68e913aca3f255ade182fc736a0581005a062","source":{"kind":"arxiv","id":"2606.26772","version":1},"attestation_state":"computed","paper":{"title":"Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Naoki Nishikawa, Satoshi Hasegawa, Shokichi Takakura","submitted_at":"2026-06-25T08:57:16Z","abstract_excerpt":"Differentially private (DP) training of neural networks is often hindered by the large amount of noise required by gradient-based methods such as DP-SGD, which repeatedly inject high-dimensional noise in parameter space throughout training. In this paper, we propose a new framework for DP learning that avoids iterative optimization in parameter space. Instead of updating the target model using privatized gradients, we employ a hypernetwork trained on public datasets to map a private dataset to the parameters of the target model. Specifically, each example is embedded into a low-dimensional rep"},"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":"2606.26772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T08:57:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ea36f4bf2cfaed0672a7af24a21c401df64fc3cb98f9d0d9c39dbbec28560bfd","abstract_canon_sha256":"67ffcc6be11556cbb951b93c509a0e6dbe2591ae71c7623b1ba1e85aa14b32ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:59.340601Z","signature_b64":"mtwr4gHu/8PFPc4prumpOWTbztJ8pf1nbR7NOzrBVbqCYswDjNV3E6jLekqAm3ekCKDfgSyoUeY44zw/YewUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e3fffbf99db48cad365e2723c68e913aca3f255ade182fc736a0581005a062","last_reissued_at":"2026-06-26T01:15:59.340212Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:59.340212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Naoki Nishikawa, Satoshi Hasegawa, Shokichi Takakura","submitted_at":"2026-06-25T08:57:16Z","abstract_excerpt":"Differentially private (DP) training of neural networks is often hindered by the large amount of noise required by gradient-based methods such as DP-SGD, which repeatedly inject high-dimensional noise in parameter space throughout training. In this paper, we propose a new framework for DP learning that avoids iterative optimization in parameter space. Instead of updating the target model using privatized gradients, we employ a hypernetwork trained on public datasets to map a private dataset to the parameters of the target model. Specifically, each example is embedded into a low-dimensional rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26772","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/2606.26772/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":"2606.26772","created_at":"2026-06-26T01:15:59.340268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26772v1","created_at":"2026-06-26T01:15:59.340268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26772","created_at":"2026-06-26T01:15:59.340268+00:00"},{"alias_kind":"pith_short_12","alias_value":"APR7767ZTW2I","created_at":"2026-06-26T01:15:59.340268+00:00"},{"alias_kind":"pith_short_16","alias_value":"APR7767ZTW2IZLJW","created_at":"2026-06-26T01:15:59.340268+00:00"},{"alias_kind":"pith_short_8","alias_value":"APR7767Z","created_at":"2026-06-26T01:15:59.340268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE","json":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE.json","graph_json":"https://pith.science/api/pith-number/APR7767ZTW2IZLJWLYTSHRUOSE/graph.json","events_json":"https://pith.science/api/pith-number/APR7767ZTW2IZLJWLYTSHRUOSE/events.json","paper":"https://pith.science/paper/APR7767Z"},"agent_actions":{"view_html":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE","download_json":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE.json","view_paper":"https://pith.science/paper/APR7767Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26772&json=true","fetch_graph":"https://pith.science/api/pith-number/APR7767ZTW2IZLJWLYTSHRUOSE/graph.json","fetch_events":"https://pith.science/api/pith-number/APR7767ZTW2IZLJWLYTSHRUOSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE/action/storage_attestation","attest_author":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE/action/author_attestation","sign_citation":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE/action/citation_signature","submit_replication":"https://pith.science/pith/APR7767ZTW2IZLJWLYTSHRUOSE/action/replication_record"}},"created_at":"2026-06-26T01:15:59.340268+00:00","updated_at":"2026-06-26T01:15:59.340268+00:00"}