{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PRWI7ZW4X3ID7OY7UKYVWLUCUY","short_pith_number":"pith:PRWI7ZW4","schema_version":"1.0","canonical_sha256":"7c6c8fe6dcbed03fbb1fa2b15b2e82a611b73f710a534920bcd371028a2bd58f","source":{"kind":"arxiv","id":"2105.05489","version":1},"attestation_state":"computed","paper":{"title":"Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Pengchuan Zhang, Shumao Zhang, Thomas Y. Hou","submitted_at":"2021-05-12T07:51:47Z","abstract_excerpt":"We propose a Multiscale Invertible Generative Network (MsIGN) and associated training algorithm that leverages multiscale structure to solve high-dimensional Bayesian inference. To address the curse of dimensionality, MsIGN exploits the low-dimensional nature of the posterior, and generates samples from coarse to fine scale (low to high dimension) by iteratively upsampling and refining samples. MsIGN is trained in a multi-stage manner to minimize the Jeffreys divergence, which avoids mode dropping in high-dimensional cases. On two high-dimensional Bayesian inverse problems, we show superior pe"},"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":"2105.05489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-05-12T07:51:47Z","cross_cats_sorted":["cs.CV","cs.LG","stat.CO"],"title_canon_sha256":"8be110c4ddf2e0413c00a57a36d67895f66aa1293bfd1a0218c4d4c3d8c9b56a","abstract_canon_sha256":"2d4ce280ba972c605da8c791432425ca9bfab3a6a3aa771e0ccd2c174b393d35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:51.475983Z","signature_b64":"KwQMw3GPP7BiwhAiMc7WBIjXFsSweAvA0ltVW0VcT3w4i6LObhnmCXrgyQbE+yNevU2SfBpihII5rJcFxR+jCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c6c8fe6dcbed03fbb1fa2b15b2e82a611b73f710a534920bcd371028a2bd58f","last_reissued_at":"2026-07-05T02:39:51.475548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:51.475548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiscale Invertible Generative Networks for High-Dimensional Bayesian Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Pengchuan Zhang, Shumao Zhang, Thomas Y. Hou","submitted_at":"2021-05-12T07:51:47Z","abstract_excerpt":"We propose a Multiscale Invertible Generative Network (MsIGN) and associated training algorithm that leverages multiscale structure to solve high-dimensional Bayesian inference. To address the curse of dimensionality, MsIGN exploits the low-dimensional nature of the posterior, and generates samples from coarse to fine scale (low to high dimension) by iteratively upsampling and refining samples. MsIGN is trained in a multi-stage manner to minimize the Jeffreys divergence, which avoids mode dropping in high-dimensional cases. On two high-dimensional Bayesian inverse problems, we show superior pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05489","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/2105.05489/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":"2105.05489","created_at":"2026-07-05T02:39:51.475607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05489v1","created_at":"2026-07-05T02:39:51.475607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05489","created_at":"2026-07-05T02:39:51.475607+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRWI7ZW4X3ID","created_at":"2026-07-05T02:39:51.475607+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRWI7ZW4X3ID7OY7","created_at":"2026-07-05T02:39:51.475607+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRWI7ZW4","created_at":"2026-07-05T02:39:51.475607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.12768","citing_title":"A Generative Framework for the Creation of Multi-Attribute Geographically-Explicit Synthetic Population","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY","json":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY.json","graph_json":"https://pith.science/api/pith-number/PRWI7ZW4X3ID7OY7UKYVWLUCUY/graph.json","events_json":"https://pith.science/api/pith-number/PRWI7ZW4X3ID7OY7UKYVWLUCUY/events.json","paper":"https://pith.science/paper/PRWI7ZW4"},"agent_actions":{"view_html":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY","download_json":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY.json","view_paper":"https://pith.science/paper/PRWI7ZW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05489&json=true","fetch_graph":"https://pith.science/api/pith-number/PRWI7ZW4X3ID7OY7UKYVWLUCUY/graph.json","fetch_events":"https://pith.science/api/pith-number/PRWI7ZW4X3ID7OY7UKYVWLUCUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY/action/storage_attestation","attest_author":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY/action/author_attestation","sign_citation":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY/action/citation_signature","submit_replication":"https://pith.science/pith/PRWI7ZW4X3ID7OY7UKYVWLUCUY/action/replication_record"}},"created_at":"2026-07-05T02:39:51.475607+00:00","updated_at":"2026-07-05T02:39:51.475607+00:00"}