{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JKTQYFNEHNRFYFZR7DN6FG67LW","short_pith_number":"pith:JKTQYFNE","schema_version":"1.0","canonical_sha256":"4aa70c15a43b625c1731f8dbe29bdf5d99a0bcb3212511e86210431de7c6aa5c","source":{"kind":"arxiv","id":"1612.04010","version":4},"attestation_state":"computed","paper":{"title":"An empirical analysis of the optimization of deep network loss surfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Jiwoong Im, Kristin Branson, Michael Tao","submitted_at":"2016-12-13T03:27:11Z","abstract_excerpt":"The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions. In this paper, we empirically investigate the loss functions of state-of-the-art networks, and how commonly-used stochastic gradient descent variants optimize these loss functions. To do this, we visualize the loss function by projecting them down to low-dimensional spaces chosen based on the convergence points of different optimization algorithms. Our observations suggest that optimization algorithms encounter and choose different descent directions at many "},"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":"1612.04010","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-13T03:27:11Z","cross_cats_sorted":[],"title_canon_sha256":"a0c67bc14eae1774808058c00fefa9243d47863d3102a5f2f8b864275d6b5698","abstract_canon_sha256":"aad78584267f1d4319df830536f49ae22e8b7eb39da6ecbe19e4f6867a0fc6d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:32.372428Z","signature_b64":"bTW5aM+XIsgEOsWbR38rOb5WhvAv0GWLzrn8cv/TkNLDfkahq4Ee5v0JtgGl9nd20SorbDbCV9bI86jmrThjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aa70c15a43b625c1731f8dbe29bdf5d99a0bcb3212511e86210431de7c6aa5c","last_reissued_at":"2026-05-18T00:28:32.371744Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:32.371744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An empirical analysis of the optimization of deep network loss surfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Jiwoong Im, Kristin Branson, Michael Tao","submitted_at":"2016-12-13T03:27:11Z","abstract_excerpt":"The success of deep neural networks hinges on our ability to accurately and efficiently optimize high-dimensional, non-convex functions. In this paper, we empirically investigate the loss functions of state-of-the-art networks, and how commonly-used stochastic gradient descent variants optimize these loss functions. To do this, we visualize the loss function by projecting them down to low-dimensional spaces chosen based on the convergence points of different optimization algorithms. Our observations suggest that optimization algorithms encounter and choose different descent directions at many "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.04010","kind":"arxiv","version":4},"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":"1612.04010","created_at":"2026-05-18T00:28:32.371871+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.04010v4","created_at":"2026-05-18T00:28:32.371871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.04010","created_at":"2026-05-18T00:28:32.371871+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKTQYFNEHNRF","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKTQYFNEHNRFYFZR","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKTQYFNE","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09044","citing_title":"Strategically Deceptive Model Deployment in Performative Prediction","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW","json":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW.json","graph_json":"https://pith.science/api/pith-number/JKTQYFNEHNRFYFZR7DN6FG67LW/graph.json","events_json":"https://pith.science/api/pith-number/JKTQYFNEHNRFYFZR7DN6FG67LW/events.json","paper":"https://pith.science/paper/JKTQYFNE"},"agent_actions":{"view_html":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW","download_json":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW.json","view_paper":"https://pith.science/paper/JKTQYFNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.04010&json=true","fetch_graph":"https://pith.science/api/pith-number/JKTQYFNEHNRFYFZR7DN6FG67LW/graph.json","fetch_events":"https://pith.science/api/pith-number/JKTQYFNEHNRFYFZR7DN6FG67LW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW/action/storage_attestation","attest_author":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW/action/author_attestation","sign_citation":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW/action/citation_signature","submit_replication":"https://pith.science/pith/JKTQYFNEHNRFYFZR7DN6FG67LW/action/replication_record"}},"created_at":"2026-05-18T00:28:32.371871+00:00","updated_at":"2026-05-18T00:28:32.371871+00:00"}