{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WY46K3XU5BVG6XMVIDWDIXAUJI","short_pith_number":"pith:WY46K3XU","schema_version":"1.0","canonical_sha256":"b639e56ef4e86a6f5d9540ec345c144a3b2eea3c1d505ffe3bd1dd9bda6be30c","source":{"kind":"arxiv","id":"1710.07746","version":3},"attestation_state":"computed","paper":{"title":"Stochastic Backward Euler: An Implicit Gradient Descent Algorithm for $k$-means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Adam Oberman, Minh Pham, Penghang Yin, Stanley Osher","submitted_at":"2017-10-21T03:02:29Z","abstract_excerpt":"In this paper, we propose an implicit gradient descent algorithm for the classic $k$-means problem. The implicit gradient step or backward Euler is solved via stochastic fixed-point iteration, in which we randomly sample a mini-batch gradient in every iteration. It is the average of the fixed-point trajectory that is carried over to the next gradient step. We draw connections between the proposed stochastic backward Euler and the recent entropy stochastic gradient descent (Entropy-SGD) for improving the training of deep neural networks. Numerical experiments on various synthetic and real datas"},"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":"1710.07746","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-21T03:02:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b69c25ebc3d78a4603f72343e05ce177135fd3f1dce18d05bdba2e57f0eb1ba3","abstract_canon_sha256":"085ab83d23d477c5cdd94eabce382111c8f4a563dc7dac74c013380f89041b44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:30.468355Z","signature_b64":"LE8ECHaCMg2JCRDEu4TuHUBXQBVWlwEV39xaRak/wczfJItZUZRGVmrvdt9xRjwiwD0/qEe3ZL1PMZhHmaOMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b639e56ef4e86a6f5d9540ec345c144a3b2eea3c1d505ffe3bd1dd9bda6be30c","last_reissued_at":"2026-05-18T00:15:30.467721Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:30.467721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Backward Euler: An Implicit Gradient Descent Algorithm for $k$-means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Adam Oberman, Minh Pham, Penghang Yin, Stanley Osher","submitted_at":"2017-10-21T03:02:29Z","abstract_excerpt":"In this paper, we propose an implicit gradient descent algorithm for the classic $k$-means problem. The implicit gradient step or backward Euler is solved via stochastic fixed-point iteration, in which we randomly sample a mini-batch gradient in every iteration. It is the average of the fixed-point trajectory that is carried over to the next gradient step. We draw connections between the proposed stochastic backward Euler and the recent entropy stochastic gradient descent (Entropy-SGD) for improving the training of deep neural networks. Numerical experiments on various synthetic and real datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07746","kind":"arxiv","version":3},"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":"1710.07746","created_at":"2026-05-18T00:15:30.467808+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.07746v3","created_at":"2026-05-18T00:15:30.467808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07746","created_at":"2026-05-18T00:15:30.467808+00:00"},{"alias_kind":"pith_short_12","alias_value":"WY46K3XU5BVG","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WY46K3XU5BVG6XMV","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WY46K3XU","created_at":"2026-05-18T12:31:53.515858+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/WY46K3XU5BVG6XMVIDWDIXAUJI","json":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI.json","graph_json":"https://pith.science/api/pith-number/WY46K3XU5BVG6XMVIDWDIXAUJI/graph.json","events_json":"https://pith.science/api/pith-number/WY46K3XU5BVG6XMVIDWDIXAUJI/events.json","paper":"https://pith.science/paper/WY46K3XU"},"agent_actions":{"view_html":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI","download_json":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI.json","view_paper":"https://pith.science/paper/WY46K3XU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.07746&json=true","fetch_graph":"https://pith.science/api/pith-number/WY46K3XU5BVG6XMVIDWDIXAUJI/graph.json","fetch_events":"https://pith.science/api/pith-number/WY46K3XU5BVG6XMVIDWDIXAUJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI/action/storage_attestation","attest_author":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI/action/author_attestation","sign_citation":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI/action/citation_signature","submit_replication":"https://pith.science/pith/WY46K3XU5BVG6XMVIDWDIXAUJI/action/replication_record"}},"created_at":"2026-05-18T00:15:30.467808+00:00","updated_at":"2026-05-18T00:15:30.467808+00:00"}