{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:CDJJKMFZULPTBORV2AW6TRYKT4","short_pith_number":"pith:CDJJKMFZ","schema_version":"1.0","canonical_sha256":"10d29530b9a2df30ba35d02de9c70a9f1a492dcd178dc649dd69d894e2bd1b3f","source":{"kind":"arxiv","id":"1506.02617","version":1},"attestation_state":"computed","paper":{"title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnam Neyshabur, Nathan Srebro, Ruslan Salakhutdinov","submitted_at":"2015-06-08T19:01:33Z","abstract_excerpt":"We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the network, and suggest Path-SGD, which is an approximate steepest descent method with respect to a path-wise regularizer related to max-norm regularization. Path-SGD is easy and efficient to implement and leads to empirical gains over SGD and AdaGrad."},"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":"1506.02617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-08T19:01:33Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"1462b0997ea14c6f3aacf841e134c4086aa1bbf0e53bdaebe06c2bd79f1778c7","abstract_canon_sha256":"c3cf518fad6b19f405f361d476040e9ff5d5bd69fd474736ca472ef440f0e3f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:55:43.756907Z","signature_b64":"CTclga1l24gKj/UoLSdwQan1BtrjOb6WIM9srrdmh59XYsQVkJRP3lspYVbDqxXTeCB/vSCIQUKYE9Vg5JEXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10d29530b9a2df30ba35d02de9c70a9f1a492dcd178dc649dd69d894e2bd1b3f","last_reissued_at":"2026-05-18T01:55:43.756201Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:55:43.756201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnam Neyshabur, Nathan Srebro, Ruslan Salakhutdinov","submitted_at":"2015-06-08T19:01:33Z","abstract_excerpt":"We revisit the choice of SGD for training deep neural networks by reconsidering the appropriate geometry in which to optimize the weights. We argue for a geometry invariant to rescaling of weights that does not affect the output of the network, and suggest Path-SGD, which is an approximate steepest descent method with respect to a path-wise regularizer related to max-norm regularization. Path-SGD is easy and efficient to implement and leads to empirical gains over SGD and AdaGrad."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.02617","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":""},"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":"1506.02617","created_at":"2026-05-18T01:55:43.756301+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.02617v1","created_at":"2026-05-18T01:55:43.756301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.02617","created_at":"2026-05-18T01:55:43.756301+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDJJKMFZULPT","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDJJKMFZULPTBORV","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDJJKMFZ","created_at":"2026-05-18T12:29:14.074870+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/CDJJKMFZULPTBORV2AW6TRYKT4","json":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4.json","graph_json":"https://pith.science/api/pith-number/CDJJKMFZULPTBORV2AW6TRYKT4/graph.json","events_json":"https://pith.science/api/pith-number/CDJJKMFZULPTBORV2AW6TRYKT4/events.json","paper":"https://pith.science/paper/CDJJKMFZ"},"agent_actions":{"view_html":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4","download_json":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4.json","view_paper":"https://pith.science/paper/CDJJKMFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.02617&json=true","fetch_graph":"https://pith.science/api/pith-number/CDJJKMFZULPTBORV2AW6TRYKT4/graph.json","fetch_events":"https://pith.science/api/pith-number/CDJJKMFZULPTBORV2AW6TRYKT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4/action/storage_attestation","attest_author":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4/action/author_attestation","sign_citation":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4/action/citation_signature","submit_replication":"https://pith.science/pith/CDJJKMFZULPTBORV2AW6TRYKT4/action/replication_record"}},"created_at":"2026-05-18T01:55:43.756301+00:00","updated_at":"2026-05-18T01:55:43.756301+00:00"}