{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LWIIEKCOCEWIZPEPOXJJQJD2HZ","short_pith_number":"pith:LWIIEKCO","schema_version":"1.0","canonical_sha256":"5d9082284e112c8cbc8f75d298247a3e74a60351e8d9a15f10cc3cc4ccd82df7","source":{"kind":"arxiv","id":"2502.11362","version":1},"attestation_state":"computed","paper":{"title":"Teleportation With Null Space Gradient Projection for Optimization Acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Aloui, Juncheng Dong, Vahid Tarokh, Zihao Wu","submitted_at":"2025-02-17T02:27:16Z","abstract_excerpt":"Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale. In particular, teleportation has emerged as a promising approach, which accelerates convergence of gradient descent-based methods by navigating within the loss invariant level set to identify parameters with advantageous geometric properties. Existing teleportation algorithms have primarily demonstrated their effectiveness in optimizing Multi-Layer Perceptrons (MLPs), but their extension to more advanced architectures, such as Convolutional Neural Networks (CNNs) and Transformers,"},"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":"2502.11362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T02:27:16Z","cross_cats_sorted":[],"title_canon_sha256":"09d5d2d43fd10d34845bf1f40721f044c5e987c3e575747d8674943ce94358a0","abstract_canon_sha256":"b568293a1263767ab6faad85f93fa6d0ed5a96923cc0bfac7a08ad01e2c7a34a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:27.184366Z","signature_b64":"4PJSPpEZlTb8P6ErfK//ySLT/YEqlHurMe+9cqAzzmIBf8t+oV0dbaASg0k1oS27FEbzEFDe6cWHkdDjSOrOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9082284e112c8cbc8f75d298247a3e74a60351e8d9a15f10cc3cc4ccd82df7","last_reissued_at":"2026-07-05T10:15:27.183879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:27.183879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teleportation With Null Space Gradient Projection for Optimization Acceleration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Aloui, Juncheng Dong, Vahid Tarokh, Zihao Wu","submitted_at":"2025-02-17T02:27:16Z","abstract_excerpt":"Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale. In particular, teleportation has emerged as a promising approach, which accelerates convergence of gradient descent-based methods by navigating within the loss invariant level set to identify parameters with advantageous geometric properties. Existing teleportation algorithms have primarily demonstrated their effectiveness in optimizing Multi-Layer Perceptrons (MLPs), but their extension to more advanced architectures, such as Convolutional Neural Networks (CNNs) and Transformers,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11362","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/2502.11362/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":"2502.11362","created_at":"2026-07-05T10:15:27.183932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11362v1","created_at":"2026-07-05T10:15:27.183932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11362","created_at":"2026-07-05T10:15:27.183932+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWIIEKCOCEWI","created_at":"2026-07-05T10:15:27.183932+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWIIEKCOCEWIZPEP","created_at":"2026-07-05T10:15:27.183932+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWIIEKCO","created_at":"2026-07-05T10:15:27.183932+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/LWIIEKCOCEWIZPEPOXJJQJD2HZ","json":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ.json","graph_json":"https://pith.science/api/pith-number/LWIIEKCOCEWIZPEPOXJJQJD2HZ/graph.json","events_json":"https://pith.science/api/pith-number/LWIIEKCOCEWIZPEPOXJJQJD2HZ/events.json","paper":"https://pith.science/paper/LWIIEKCO"},"agent_actions":{"view_html":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ","download_json":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ.json","view_paper":"https://pith.science/paper/LWIIEKCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11362&json=true","fetch_graph":"https://pith.science/api/pith-number/LWIIEKCOCEWIZPEPOXJJQJD2HZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LWIIEKCOCEWIZPEPOXJJQJD2HZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ/action/storage_attestation","attest_author":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ/action/author_attestation","sign_citation":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ/action/citation_signature","submit_replication":"https://pith.science/pith/LWIIEKCOCEWIZPEPOXJJQJD2HZ/action/replication_record"}},"created_at":"2026-07-05T10:15:27.183932+00:00","updated_at":"2026-07-05T10:15:27.183932+00:00"}