{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AB2NEK64LNDMKV6U33OQTUB5AN","short_pith_number":"pith:AB2NEK64","schema_version":"1.0","canonical_sha256":"0074d22bdc5b46c557d4dedd09d03d0373a8e3d9533319225c079e57b06492c5","source":{"kind":"arxiv","id":"2307.10099","version":1},"attestation_state":"computed","paper":{"title":"Memory Efficient And Minimax Distribution Estimation Under Wasserstein Distance Using Bayesian Histograms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Anirban Bhattacharya, Debdeep Pati, Lekha Patel, Peter Matthew Jacobs","submitted_at":"2023-07-19T16:13:20Z","abstract_excerpt":"We study Bayesian histograms for distribution estimation on $[0,1]^d$ under the Wasserstein $W_v, 1 \\leq v < \\infty$ distance in the i.i.d sampling regime. We newly show that when $d < 2v$, histograms possess a special \\textit{memory efficiency} property, whereby in reference to the sample size $n$, order $n^{d/2v}$ bins are needed to obtain minimax rate optimality. This result holds for the posterior mean histogram and with respect to posterior contraction: under the class of Borel probability measures and some classes of smooth densities. The attained memory footprint overcomes existing mini"},"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":"2307.10099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2023-07-19T16:13:20Z","cross_cats_sorted":["stat.CO","stat.ML","stat.TH"],"title_canon_sha256":"017e97d6f6368cba4ec1d868a9da86b56a8218261856ebc25762bb8ae3b24c6b","abstract_canon_sha256":"6a84ce6756c48aed3089588513a9533cfb72e0ba826c9e672552752e36b1330e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:50.631151Z","signature_b64":"XsatTVHWP1dvd/Qmw7d/koo3nRAiADj55YBNCEk6ggwR18S47sOkU38gliDIISiCiVD1DlkBnI5LQt+/1jTTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0074d22bdc5b46c557d4dedd09d03d0373a8e3d9533319225c079e57b06492c5","last_reissued_at":"2026-07-05T06:32:50.630753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:50.630753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Efficient And Minimax Distribution Estimation Under Wasserstein Distance Using Bayesian Histograms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Anirban Bhattacharya, Debdeep Pati, Lekha Patel, Peter Matthew Jacobs","submitted_at":"2023-07-19T16:13:20Z","abstract_excerpt":"We study Bayesian histograms for distribution estimation on $[0,1]^d$ under the Wasserstein $W_v, 1 \\leq v < \\infty$ distance in the i.i.d sampling regime. We newly show that when $d < 2v$, histograms possess a special \\textit{memory efficiency} property, whereby in reference to the sample size $n$, order $n^{d/2v}$ bins are needed to obtain minimax rate optimality. This result holds for the posterior mean histogram and with respect to posterior contraction: under the class of Borel probability measures and some classes of smooth densities. The attained memory footprint overcomes existing mini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10099","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.10099/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2307.10099","created_at":"2026-07-05T06:32:50.630815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10099v1","created_at":"2026-07-05T06:32:50.630815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10099","created_at":"2026-07-05T06:32:50.630815+00:00"},{"alias_kind":"pith_short_12","alias_value":"AB2NEK64LNDM","created_at":"2026-07-05T06:32:50.630815+00:00"},{"alias_kind":"pith_short_16","alias_value":"AB2NEK64LNDMKV6U","created_at":"2026-07-05T06:32:50.630815+00:00"},{"alias_kind":"pith_short_8","alias_value":"AB2NEK64","created_at":"2026-07-05T06:32:50.630815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17856","citing_title":"Stochastic Weight Sharing for Bayesian Neural Networks","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN","json":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN.json","graph_json":"https://pith.science/api/pith-number/AB2NEK64LNDMKV6U33OQTUB5AN/graph.json","events_json":"https://pith.science/api/pith-number/AB2NEK64LNDMKV6U33OQTUB5AN/events.json","paper":"https://pith.science/paper/AB2NEK64"},"agent_actions":{"view_html":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN","download_json":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN.json","view_paper":"https://pith.science/paper/AB2NEK64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10099&json=true","fetch_graph":"https://pith.science/api/pith-number/AB2NEK64LNDMKV6U33OQTUB5AN/graph.json","fetch_events":"https://pith.science/api/pith-number/AB2NEK64LNDMKV6U33OQTUB5AN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN/action/storage_attestation","attest_author":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN/action/author_attestation","sign_citation":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN/action/citation_signature","submit_replication":"https://pith.science/pith/AB2NEK64LNDMKV6U33OQTUB5AN/action/replication_record"}},"created_at":"2026-07-05T06:32:50.630815+00:00","updated_at":"2026-07-05T06:32:50.630815+00:00"}