{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5BLQ2JLIEI5VQQA7JOK76IH3TA","short_pith_number":"pith:5BLQ2JLI","schema_version":"1.0","canonical_sha256":"e8570d2568223b58401f4b95ff20fb9834af54541f32d74dd9429d3c49586448","source":{"kind":"arxiv","id":"2604.09412","version":2},"attestation_state":"computed","paper":{"title":"Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Local minima in two-layer ReLU networks admit an exact low-dimensional representation via summary statistics.","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bruno Loureiro, Jie Huang, Stefano Sarao Mannelli","submitted_at":"2026-04-10T15:26:00Z","abstract_excerpt":"We study the population loss landscape of two-layer ReLU networks of the form $\\sum_{k=1}^K \\mathrm{ReLU}(w_k^\\top x)$ in a realisable teacher-student setting with Gaussian covariates. We show that local minima admit an exact low-dimensional representation in terms of summary statistics, yielding a sharp and interpretable characterisation of the landscape. We further establish a direct link with one-pass SGD: local minima correspond to attractive fixed points of the dynamics in summary statistics space. This perspective reveals a hierarchical organisation of minima into discrete families and s"},"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":"2604.09412","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-04-10T15:26:00Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"2758a56d67f00d43bd6fb4300fc3a3330478542021269a49b3f30e34303d05b3","abstract_canon_sha256":"2b457ee33e7d83e54e093d13c42311766f8d2c24a201b3cd3dc40cb9add9b499"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:52.800380Z","signature_b64":"QXikZk7WOCmV3HLRQfWdUwZRtSje0IdYNeKzXMIe7YRxfxK0PH+dkoCn4r02kDOyw54IJq4OiNSiVNcNpx34BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8570d2568223b58401f4b95ff20fb9834af54541f32d74dd9429d3c49586448","last_reissued_at":"2026-06-01T01:03:52.799059Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:52.799059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Local minima in two-layer ReLU networks admit an exact low-dimensional representation via summary statistics.","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bruno Loureiro, Jie Huang, Stefano Sarao Mannelli","submitted_at":"2026-04-10T15:26:00Z","abstract_excerpt":"We study the population loss landscape of two-layer ReLU networks of the form $\\sum_{k=1}^K \\mathrm{ReLU}(w_k^\\top x)$ in a realisable teacher-student setting with Gaussian covariates. We show that local minima admit an exact low-dimensional representation in terms of summary statistics, yielding a sharp and interpretable characterisation of the landscape. We further establish a direct link with one-pass SGD: local minima correspond to attractive fixed points of the dynamics in summary statistics space. This perspective reveals a hierarchical organisation of minima into discrete families and s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that local minima admit an exact low-dimensional representation in terms of summary statistics, yielding a sharp and interpretable characterisation of the landscape. We further establish a direct link with one-pass SGD: local minima correspond to attractive fixed points of the dynamics in summary statistics space.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The analysis assumes a realizable teacher-student setting with Gaussian covariates and the specific network form sum ReLU(w_k^T x), which may not hold for more general data distributions or deeper networks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Local minima of two-layer ReLU networks have an exact representation in terms of a few summary statistics that correspond to attractive fixed points of one-pass SGD, with overparameterization connecting them via flat directions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Local minima in two-layer ReLU networks admit an exact low-dimensional representation via summary statistics.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"31ccac97a9566736aafa280aed4efca3f48892e16d0f876f7b6b90cb8bc34c6b"},"source":{"id":"2604.09412","kind":"arxiv","version":2},"verdict":{"id":"8ab2454f-330d-4b3e-8713-83315da1a67c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:40:16.865754Z","strongest_claim":"We show that local minima admit an exact low-dimensional representation in terms of summary statistics, yielding a sharp and interpretable characterisation of the landscape. We further establish a direct link with one-pass SGD: local minima correspond to attractive fixed points of the dynamics in summary statistics space.","one_line_summary":"Local minima of two-layer ReLU networks have an exact representation in terms of a few summary statistics that correspond to attractive fixed points of one-pass SGD, with overparameterization connecting them via flat directions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The analysis assumes a realizable teacher-student setting with Gaussian covariates and the specific network form sum ReLU(w_k^T x), which may not hold for more general data distributions or deeper networks.","pith_extraction_headline":"Local minima in two-layer ReLU networks admit an exact low-dimensional representation via summary statistics."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09412/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":"2604.09412","created_at":"2026-06-01T01:03:52.799223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09412v2","created_at":"2026-06-01T01:03:52.799223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09412","created_at":"2026-06-01T01:03:52.799223+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BLQ2JLIEI5V","created_at":"2026-06-01T01:03:52.799223+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BLQ2JLIEI5VQQA7","created_at":"2026-06-01T01:03:52.799223+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BLQ2JLI","created_at":"2026-06-01T01:03:52.799223+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/5BLQ2JLIEI5VQQA7JOK76IH3TA","json":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA.json","graph_json":"https://pith.science/api/pith-number/5BLQ2JLIEI5VQQA7JOK76IH3TA/graph.json","events_json":"https://pith.science/api/pith-number/5BLQ2JLIEI5VQQA7JOK76IH3TA/events.json","paper":"https://pith.science/paper/5BLQ2JLI"},"agent_actions":{"view_html":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA","download_json":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA.json","view_paper":"https://pith.science/paper/5BLQ2JLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09412&json=true","fetch_graph":"https://pith.science/api/pith-number/5BLQ2JLIEI5VQQA7JOK76IH3TA/graph.json","fetch_events":"https://pith.science/api/pith-number/5BLQ2JLIEI5VQQA7JOK76IH3TA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA/action/storage_attestation","attest_author":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA/action/author_attestation","sign_citation":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA/action/citation_signature","submit_replication":"https://pith.science/pith/5BLQ2JLIEI5VQQA7JOK76IH3TA/action/replication_record"}},"created_at":"2026-06-01T01:03:52.799223+00:00","updated_at":"2026-06-01T01:03:52.799223+00:00"}