{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ARYSVVYBFNYIAAGGWRTB2GVC5A","short_pith_number":"pith:ARYSVVYB","schema_version":"1.0","canonical_sha256":"04712ad7012b708000c6b4661d1aa2e809f56239bc9788bb6bab17d732818c9e","source":{"kind":"arxiv","id":"1803.01927","version":1},"attestation_state":"computed","paper":{"title":"Energy-entropy competition and the effectiveness of stochastic gradient descent in machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alpha A. Lee, Andrew M. Saxe, Madhu S. Advani, Yao Zhang","submitted_at":"2018-03-05T21:12:04Z","abstract_excerpt":"Finding parameters that minimise a loss function is at the core of many machine learning methods. The Stochastic Gradient Descent algorithm is widely used and delivers state of the art results for many problems. Nonetheless, Stochastic Gradient Descent typically cannot find the global minimum, thus its empirical effectiveness is hitherto mysterious. We derive a correspondence between parameter inference and free energy minimisation in statistical physics. The degree of undersampling plays the role of temperature. Analogous to the energy-entropy competition in statistical physics, wide but shal"},"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":"1803.01927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T21:12:04Z","cross_cats_sorted":["cond-mat.stat-mech","stat.ML"],"title_canon_sha256":"18420b225b5890d6fce44e217c642a6680b115a68f77db8e98cd363e9c3c6b6d","abstract_canon_sha256":"6d6126c22b69b5c8646cde620ef17a77e4b27bc92d50871b0be4484844793b13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:59.333449Z","signature_b64":"qTMAtcLKEVcZfYNi/Uhe3FoLfWuZkduTeURXwb+KPJU0nBOCOlPRN9mQ+RHuDZs0TYn9Q0r9xQyW478zON92Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04712ad7012b708000c6b4661d1aa2e809f56239bc9788bb6bab17d732818c9e","last_reissued_at":"2026-05-18T00:04:59.333001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:59.333001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-entropy competition and the effectiveness of stochastic gradient descent in machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alpha A. Lee, Andrew M. Saxe, Madhu S. Advani, Yao Zhang","submitted_at":"2018-03-05T21:12:04Z","abstract_excerpt":"Finding parameters that minimise a loss function is at the core of many machine learning methods. The Stochastic Gradient Descent algorithm is widely used and delivers state of the art results for many problems. Nonetheless, Stochastic Gradient Descent typically cannot find the global minimum, thus its empirical effectiveness is hitherto mysterious. We derive a correspondence between parameter inference and free energy minimisation in statistical physics. The degree of undersampling plays the role of temperature. Analogous to the energy-entropy competition in statistical physics, wide but shal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01927","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":"1803.01927","created_at":"2026-05-18T00:04:59.333070+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01927v1","created_at":"2026-05-18T00:04:59.333070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01927","created_at":"2026-05-18T00:04:59.333070+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARYSVVYBFNYI","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARYSVVYBFNYIAAGG","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARYSVVYB","created_at":"2026-05-18T12:32:13.499390+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/ARYSVVYBFNYIAAGGWRTB2GVC5A","json":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A.json","graph_json":"https://pith.science/api/pith-number/ARYSVVYBFNYIAAGGWRTB2GVC5A/graph.json","events_json":"https://pith.science/api/pith-number/ARYSVVYBFNYIAAGGWRTB2GVC5A/events.json","paper":"https://pith.science/paper/ARYSVVYB"},"agent_actions":{"view_html":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A","download_json":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A.json","view_paper":"https://pith.science/paper/ARYSVVYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01927&json=true","fetch_graph":"https://pith.science/api/pith-number/ARYSVVYBFNYIAAGGWRTB2GVC5A/graph.json","fetch_events":"https://pith.science/api/pith-number/ARYSVVYBFNYIAAGGWRTB2GVC5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A/action/storage_attestation","attest_author":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A/action/author_attestation","sign_citation":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A/action/citation_signature","submit_replication":"https://pith.science/pith/ARYSVVYBFNYIAAGGWRTB2GVC5A/action/replication_record"}},"created_at":"2026-05-18T00:04:59.333070+00:00","updated_at":"2026-05-18T00:04:59.333070+00:00"}