{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YVPNKVPI7R53O2MLPKMMVTDE2U","short_pith_number":"pith:YVPNKVPI","schema_version":"1.0","canonical_sha256":"c55ed555e8fc7bb7698b7a98cacc64d51bc8b342f12559e268724f3d0483f278","source":{"kind":"arxiv","id":"1608.04980","version":1},"attestation_state":"computed","paper":{"title":"Mollifying Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Francesco Visin, Marcin Moczulski, Yoshua Bengio","submitted_at":"2016-08-17T14:37:34Z","abstract_excerpt":"The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e.g. it can involve pathological landscapes such as saddle-surfaces that can be difficult to escape for algorithms based on simple gradient descent. In this paper, we attack the problem of optimization of highly non-convex neural networks by starting with a smoothed -- or \\textit{mollified} -- objective function that gradually has a more non-convex energy landscape during the training. Our proposition is inspired by the recent "},"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":"1608.04980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-17T14:37:34Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"98edc6f995b1d3ee435beb74dba242e3ee76356d7c50d6b8c490a4a15aaf94ac","abstract_canon_sha256":"3bac4f721315f01388a3f7397a50a3fd0df4796f84797c98e317a1adb32864ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:33.085069Z","signature_b64":"eY5ELKsqAha/9BAGKWE6H2OubnjJwr03uVuH1A/JHf81bx984QTmZ6y5p/djPxGAJFqLxkZcXoAo9OJvKwikDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c55ed555e8fc7bb7698b7a98cacc64d51bc8b342f12559e268724f3d0483f278","last_reissued_at":"2026-05-18T01:08:33.084428Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:33.084428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mollifying Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Caglar Gulcehre, Francesco Visin, Marcin Moczulski, Yoshua Bengio","submitted_at":"2016-08-17T14:37:34Z","abstract_excerpt":"The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e.g. it can involve pathological landscapes such as saddle-surfaces that can be difficult to escape for algorithms based on simple gradient descent. In this paper, we attack the problem of optimization of highly non-convex neural networks by starting with a smoothed -- or \\textit{mollified} -- objective function that gradually has a more non-convex energy landscape during the training. Our proposition is inspired by the recent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04980","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":"1608.04980","created_at":"2026-05-18T01:08:33.084542+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.04980v1","created_at":"2026-05-18T01:08:33.084542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04980","created_at":"2026-05-18T01:08:33.084542+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVPNKVPI7R53","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVPNKVPI7R53O2ML","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVPNKVPI","created_at":"2026-05-18T12:30:53.716459+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/YVPNKVPI7R53O2MLPKMMVTDE2U","json":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U.json","graph_json":"https://pith.science/api/pith-number/YVPNKVPI7R53O2MLPKMMVTDE2U/graph.json","events_json":"https://pith.science/api/pith-number/YVPNKVPI7R53O2MLPKMMVTDE2U/events.json","paper":"https://pith.science/paper/YVPNKVPI"},"agent_actions":{"view_html":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U","download_json":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U.json","view_paper":"https://pith.science/paper/YVPNKVPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.04980&json=true","fetch_graph":"https://pith.science/api/pith-number/YVPNKVPI7R53O2MLPKMMVTDE2U/graph.json","fetch_events":"https://pith.science/api/pith-number/YVPNKVPI7R53O2MLPKMMVTDE2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U/action/storage_attestation","attest_author":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U/action/author_attestation","sign_citation":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U/action/citation_signature","submit_replication":"https://pith.science/pith/YVPNKVPI7R53O2MLPKMMVTDE2U/action/replication_record"}},"created_at":"2026-05-18T01:08:33.084542+00:00","updated_at":"2026-05-18T01:08:33.084542+00:00"}