{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:554HHUEVRWFSL6T457PIV7XI4G","short_pith_number":"pith:554HHUEV","schema_version":"1.0","canonical_sha256":"ef7873d0958d8b25fa7cefde8afee8e192351de3acc4213fd1d215d5a24ba8c1","source":{"kind":"arxiv","id":"1605.00529","version":1},"attestation_state":"computed","paper":{"title":"Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Amin Karbasi, Andreas Krause, Mario Lucic, Mesrob I. Ohannessian","submitted_at":"2016-05-02T15:32:14Z","abstract_excerpt":"Faced with massive data, is it possible to trade off (statistical) risk, and (computational) space and time? This challenge lies at the heart of large-scale machine learning. Using k-means clustering as a prototypical unsupervised learning problem, we show how we can strategically summarize the data (control space) in order to trade off risk and time when data is generated by a probabilistic model. Our summarization is based on coreset constructions from computational geometry. We also develop an algorithm, TRAM, to navigate the space/time/data/risk tradeoff in practice. In particular, we show"},"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":"1605.00529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-02T15:32:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ce3897ee54914a5f67915115d35d5cf802820a84c45380c4dd90fd7ae2b9270b","abstract_canon_sha256":"b564af441603af70751e5d2820567386b08e84240f8da1961ec1514c6bbd1054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:48.436549Z","signature_b64":"wXjgJcmLULiCPH4OoSMyVY7TS/i52/ghx0tSOiAlGuRC/Rxg0PGxPJmfH5jjmVa89/7wZ0piXgY/kbLRhZxBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7873d0958d8b25fa7cefde8afee8e192351de3acc4213fd1d215d5a24ba8c1","last_reissued_at":"2026-05-18T01:15:48.436065Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:48.436065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Amin Karbasi, Andreas Krause, Mario Lucic, Mesrob I. Ohannessian","submitted_at":"2016-05-02T15:32:14Z","abstract_excerpt":"Faced with massive data, is it possible to trade off (statistical) risk, and (computational) space and time? This challenge lies at the heart of large-scale machine learning. Using k-means clustering as a prototypical unsupervised learning problem, we show how we can strategically summarize the data (control space) in order to trade off risk and time when data is generated by a probabilistic model. Our summarization is based on coreset constructions from computational geometry. We also develop an algorithm, TRAM, to navigate the space/time/data/risk tradeoff in practice. In particular, we show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.00529","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":"1605.00529","created_at":"2026-05-18T01:15:48.436151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.00529v1","created_at":"2026-05-18T01:15:48.436151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.00529","created_at":"2026-05-18T01:15:48.436151+00:00"},{"alias_kind":"pith_short_12","alias_value":"554HHUEVRWFS","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"554HHUEVRWFSL6T4","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"554HHUEV","created_at":"2026-05-18T12:29:58.707656+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/554HHUEVRWFSL6T457PIV7XI4G","json":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G.json","graph_json":"https://pith.science/api/pith-number/554HHUEVRWFSL6T457PIV7XI4G/graph.json","events_json":"https://pith.science/api/pith-number/554HHUEVRWFSL6T457PIV7XI4G/events.json","paper":"https://pith.science/paper/554HHUEV"},"agent_actions":{"view_html":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G","download_json":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G.json","view_paper":"https://pith.science/paper/554HHUEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.00529&json=true","fetch_graph":"https://pith.science/api/pith-number/554HHUEVRWFSL6T457PIV7XI4G/graph.json","fetch_events":"https://pith.science/api/pith-number/554HHUEVRWFSL6T457PIV7XI4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G/action/storage_attestation","attest_author":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G/action/author_attestation","sign_citation":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G/action/citation_signature","submit_replication":"https://pith.science/pith/554HHUEVRWFSL6T457PIV7XI4G/action/replication_record"}},"created_at":"2026-05-18T01:15:48.436151+00:00","updated_at":"2026-05-18T01:15:48.436151+00:00"}