{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LNXT2RHORHRB2VD3VE3YVV47C7","short_pith_number":"pith:LNXT2RHO","schema_version":"1.0","canonical_sha256":"5b6f3d44ee89e21d547ba9378ad79f17f376b0abfb3beba185b4c28156d73e8a","source":{"kind":"arxiv","id":"1803.04386","version":2},"attestation_state":"computed","paper":{"title":"Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dustin Tran, Jimmy Ba, Paul Vicol, Roger Grosse, Yeming Wen","submitted_at":"2018-03-12T17:25:21Z","abstract_excerpt":"Stochastic neural net weights are used in a variety of contexts, including regularization, Bayesian neural nets, exploration in reinforcement learning, and evolution strategies. Unfortunately, due to the large number of weights, all the examples in a mini-batch typically share the same weight perturbation, thereby limiting the variance reduction effect of large mini-batches. We introduce flipout, an efficient method for decorrelating the gradients within a mini-batch by implicitly sampling pseudo-independent weight perturbations for each example. Empirically, flipout achieves the ideal linear "},"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":"1803.04386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-12T17:25:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"598ee77c4873ba38bf9286cb58d065b290d31328dc9f1a6fec110ce468ccfec8","abstract_canon_sha256":"1ce9b2664116399ab431de781be2c0e8998a24e6794b9897c55567032dd56f1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:41.005310Z","signature_b64":"iAsPIbWqedeuOdUo/zxkvHLb/o5owXQqWxMIC6oGM0XFvGDmFeJqJVgZ/WfyDq0pKOhDWRhkBRTAo9Yz7qXwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b6f3d44ee89e21d547ba9378ad79f17f376b0abfb3beba185b4c28156d73e8a","last_reissued_at":"2026-05-18T00:19:41.004665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:41.004665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dustin Tran, Jimmy Ba, Paul Vicol, Roger Grosse, Yeming Wen","submitted_at":"2018-03-12T17:25:21Z","abstract_excerpt":"Stochastic neural net weights are used in a variety of contexts, including regularization, Bayesian neural nets, exploration in reinforcement learning, and evolution strategies. Unfortunately, due to the large number of weights, all the examples in a mini-batch typically share the same weight perturbation, thereby limiting the variance reduction effect of large mini-batches. We introduce flipout, an efficient method for decorrelating the gradients within a mini-batch by implicitly sampling pseudo-independent weight perturbations for each example. Empirically, flipout achieves the ideal linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04386","kind":"arxiv","version":2},"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":"1803.04386","created_at":"2026-05-18T00:19:41.004761+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.04386v2","created_at":"2026-05-18T00:19:41.004761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04386","created_at":"2026-05-18T00:19:41.004761+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNXT2RHORHRB","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNXT2RHORHRB2VD3","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNXT2RHO","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22593","citing_title":"Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7","json":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7.json","graph_json":"https://pith.science/api/pith-number/LNXT2RHORHRB2VD3VE3YVV47C7/graph.json","events_json":"https://pith.science/api/pith-number/LNXT2RHORHRB2VD3VE3YVV47C7/events.json","paper":"https://pith.science/paper/LNXT2RHO"},"agent_actions":{"view_html":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7","download_json":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7.json","view_paper":"https://pith.science/paper/LNXT2RHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.04386&json=true","fetch_graph":"https://pith.science/api/pith-number/LNXT2RHORHRB2VD3VE3YVV47C7/graph.json","fetch_events":"https://pith.science/api/pith-number/LNXT2RHORHRB2VD3VE3YVV47C7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7/action/storage_attestation","attest_author":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7/action/author_attestation","sign_citation":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7/action/citation_signature","submit_replication":"https://pith.science/pith/LNXT2RHORHRB2VD3VE3YVV47C7/action/replication_record"}},"created_at":"2026-05-18T00:19:41.004761+00:00","updated_at":"2026-05-18T00:19:41.004761+00:00"}