{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4KMQ2ZNG4S774OPKUVKHV32HXC","short_pith_number":"pith:4KMQ2ZNG","schema_version":"1.0","canonical_sha256":"e2990d65a6e4bffe39eaa5547aef47b8b7b605637cebc78bc3f9ed8ff95ca297","source":{"kind":"arxiv","id":"2106.05480","version":2},"attestation_state":"computed","paper":{"title":"Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Kevin Tian, Ruoqi Shen, Yin Tat Lee","submitted_at":"2021-06-10T03:47:39Z","abstract_excerpt":"We give lower bounds on the performance of two of the most popular sampling methods in practice, the Metropolis-adjusted Langevin algorithm (MALA) and multi-step Hamiltonian Monte Carlo (HMC) with a leapfrog integrator, when applied to well-conditioned distributions. Our main result is a nearly-tight lower bound of $\\widetilde{\\Omega}(\\kappa d)$ on the mixing time of MALA from an exponentially warm start, matching a line of algorithmic results up to logarithmic factors and answering an open question of Chewi et. al. We also show that a polynomial dependence on dimension is necessary for the re"},"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":"2106.05480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2021-06-10T03:47:39Z","cross_cats_sorted":["cs.CC","cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"c70aa42573a9e8350f6f195f1e0f08ea909788c7e7d10b99a300f19209906b0e","abstract_canon_sha256":"0c2c9459ca60ba04c3f001f8108b994f3366985e7bd46e34aff802f81c86f665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:18.036431Z","signature_b64":"vSyQjt0dUWb8x+lYDOyE+mk9n6OMk8mUtcvUuV7ECDHi3w8olUy5Cpw1U1uShZYXjzf5wswq0UuaZG2FCpBhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2990d65a6e4bffe39eaa5547aef47b8b7b605637cebc78bc3f9ed8ff95ca297","last_reissued_at":"2026-07-05T03:26:18.035903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:18.035903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Kevin Tian, Ruoqi Shen, Yin Tat Lee","submitted_at":"2021-06-10T03:47:39Z","abstract_excerpt":"We give lower bounds on the performance of two of the most popular sampling methods in practice, the Metropolis-adjusted Langevin algorithm (MALA) and multi-step Hamiltonian Monte Carlo (HMC) with a leapfrog integrator, when applied to well-conditioned distributions. Our main result is a nearly-tight lower bound of $\\widetilde{\\Omega}(\\kappa d)$ on the mixing time of MALA from an exponentially warm start, matching a line of algorithmic results up to logarithmic factors and answering an open question of Chewi et. al. We also show that a polynomial dependence on dimension is necessary for the re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05480","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.05480/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":"2106.05480","created_at":"2026-07-05T03:26:18.035967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.05480v2","created_at":"2026-07-05T03:26:18.035967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05480","created_at":"2026-07-05T03:26:18.035967+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KMQ2ZNG4S77","created_at":"2026-07-05T03:26:18.035967+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KMQ2ZNG4S774OPK","created_at":"2026-07-05T03:26:18.035967+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KMQ2ZNG","created_at":"2026-07-05T03:26:18.035967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13259","citing_title":"On Accelerated Mixing of the No-U-turn Sampler","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC","json":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC.json","graph_json":"https://pith.science/api/pith-number/4KMQ2ZNG4S774OPKUVKHV32HXC/graph.json","events_json":"https://pith.science/api/pith-number/4KMQ2ZNG4S774OPKUVKHV32HXC/events.json","paper":"https://pith.science/paper/4KMQ2ZNG"},"agent_actions":{"view_html":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC","download_json":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC.json","view_paper":"https://pith.science/paper/4KMQ2ZNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.05480&json=true","fetch_graph":"https://pith.science/api/pith-number/4KMQ2ZNG4S774OPKUVKHV32HXC/graph.json","fetch_events":"https://pith.science/api/pith-number/4KMQ2ZNG4S774OPKUVKHV32HXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC/action/storage_attestation","attest_author":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC/action/author_attestation","sign_citation":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC/action/citation_signature","submit_replication":"https://pith.science/pith/4KMQ2ZNG4S774OPKUVKHV32HXC/action/replication_record"}},"created_at":"2026-07-05T03:26:18.035967+00:00","updated_at":"2026-07-05T03:26:18.035967+00:00"}