{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KHTUIXFYLMYUBCU3CSPW5IONCB","short_pith_number":"pith:KHTUIXFY","canonical_record":{"source":{"id":"1903.12416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-29T09:41:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ccbed43c5625f09bc94a1d51ad7df3c8c85a351bc2a4bf26b99215837d825c10","abstract_canon_sha256":"902fdf117ed128c3ad0852fff63539767cfaa3e09856d9115e56b5aa0aa0f8dd"},"schema_version":"1.0"},"canonical_sha256":"51e7445cb85b31408a9b149f6ea1cd1073072b1e387b00c5992a1788a6761d64","source":{"kind":"arxiv","id":"1903.12416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.12416","created_at":"2026-05-17T23:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"1903.12416v1","created_at":"2026-05-17T23:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12416","created_at":"2026-05-17T23:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"KHTUIXFYLMYU","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KHTUIXFYLMYUBCU3","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KHTUIXFY","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KHTUIXFYLMYUBCU3CSPW5IONCB","target":"record","payload":{"canonical_record":{"source":{"id":"1903.12416","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-29T09:41:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ccbed43c5625f09bc94a1d51ad7df3c8c85a351bc2a4bf26b99215837d825c10","abstract_canon_sha256":"902fdf117ed128c3ad0852fff63539767cfaa3e09856d9115e56b5aa0aa0f8dd"},"schema_version":"1.0"},"canonical_sha256":"51e7445cb85b31408a9b149f6ea1cd1073072b1e387b00c5992a1788a6761d64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:54.102863Z","signature_b64":"tyYFjhkW1GHsuuOWz1IWu7bBzbp334MGmiqjlCfZCPYT6HU4nEwmNNysIXs08389NMig14KhM5O4ijWvPSMBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51e7445cb85b31408a9b149f6ea1cd1073072b1e387b00c5992a1788a6761d64","last_reissued_at":"2026-05-17T23:49:54.102265Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:54.102265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.12416","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ilk3ghDYHY9klSx1n/CNqtRpACJu/oWFxCaq26IB0F9n1XWibca/quDm2cDHU+DZZZTcLY7pI1Kl3RQiSiUiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:42:40.064558Z"},"content_sha256":"59112f6e06a8c3dad5304476b0f9333ef43c252cb989b0cfbe6460341aac353b","schema_version":"1.0","event_id":"sha256:59112f6e06a8c3dad5304476b0f9333ef43c252cb989b0cfbe6460341aac353b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KHTUIXFYLMYUBCU3CSPW5IONCB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Variance Reduction with Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Kfir Y. Levy, Sebastian Curi, Zal\\'an Borsos","submitted_at":"2019-03-29T09:41:57Z","abstract_excerpt":"Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction. In this work, we propose a new framework for variance reduction that enables the use of mixtures over predefined sampling distributions, which can naturally encode prior knowledge about the data. While these sampling distributions are fixed, the mixture weights are adapted during the optimization process. We propose VRM, a novel and efficient adaptive scheme that asymptotically recovers the best mixture weights in hindsight and can also accommodate sampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12416","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGG7FvjGn408bso7lopkRVto/mMBt6xWtfNX76+zNcFTqnZo40zl39Dg9BAu5/QRuTkWVpoGN5wMf3hvlArECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:42:40.065217Z"},"content_sha256":"f87e7d0976984aef228829be0fd4ce0f1adc543a76e2619e0a2f59605d996246","schema_version":"1.0","event_id":"sha256:f87e7d0976984aef228829be0fd4ce0f1adc543a76e2619e0a2f59605d996246"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHTUIXFYLMYUBCU3CSPW5IONCB/bundle.json","state_url":"https://pith.science/pith/KHTUIXFYLMYUBCU3CSPW5IONCB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHTUIXFYLMYUBCU3CSPW5IONCB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T21:42:40Z","links":{"resolver":"https://pith.science/pith/KHTUIXFYLMYUBCU3CSPW5IONCB","bundle":"https://pith.science/pith/KHTUIXFYLMYUBCU3CSPW5IONCB/bundle.json","state":"https://pith.science/pith/KHTUIXFYLMYUBCU3CSPW5IONCB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHTUIXFYLMYUBCU3CSPW5IONCB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KHTUIXFYLMYUBCU3CSPW5IONCB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"902fdf117ed128c3ad0852fff63539767cfaa3e09856d9115e56b5aa0aa0f8dd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-29T09:41:57Z","title_canon_sha256":"ccbed43c5625f09bc94a1d51ad7df3c8c85a351bc2a4bf26b99215837d825c10"},"schema_version":"1.0","source":{"id":"1903.12416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.12416","created_at":"2026-05-17T23:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"1903.12416v1","created_at":"2026-05-17T23:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12416","created_at":"2026-05-17T23:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"KHTUIXFYLMYU","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KHTUIXFYLMYUBCU3","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KHTUIXFY","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:f87e7d0976984aef228829be0fd4ce0f1adc543a76e2619e0a2f59605d996246","target":"graph","created_at":"2026-05-17T23:49:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Adaptive importance sampling for stochastic optimization is a promising approach that offers improved convergence through variance reduction. In this work, we propose a new framework for variance reduction that enables the use of mixtures over predefined sampling distributions, which can naturally encode prior knowledge about the data. While these sampling distributions are fixed, the mixture weights are adapted during the optimization process. We propose VRM, a novel and efficient adaptive scheme that asymptotically recovers the best mixture weights in hindsight and can also accommodate sampl","authors_text":"Andreas Krause, Kfir Y. Levy, Sebastian Curi, Zal\\'an Borsos","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-29T09:41:57Z","title":"Online Variance Reduction with Mixtures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12416","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:59112f6e06a8c3dad5304476b0f9333ef43c252cb989b0cfbe6460341aac353b","target":"record","created_at":"2026-05-17T23:49:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"902fdf117ed128c3ad0852fff63539767cfaa3e09856d9115e56b5aa0aa0f8dd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-29T09:41:57Z","title_canon_sha256":"ccbed43c5625f09bc94a1d51ad7df3c8c85a351bc2a4bf26b99215837d825c10"},"schema_version":"1.0","source":{"id":"1903.12416","kind":"arxiv","version":1}},"canonical_sha256":"51e7445cb85b31408a9b149f6ea1cd1073072b1e387b00c5992a1788a6761d64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51e7445cb85b31408a9b149f6ea1cd1073072b1e387b00c5992a1788a6761d64","first_computed_at":"2026-05-17T23:49:54.102265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:54.102265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tyYFjhkW1GHsuuOWz1IWu7bBzbp334MGmiqjlCfZCPYT6HU4nEwmNNysIXs08389NMig14KhM5O4ijWvPSMBAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:54.102863Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.12416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59112f6e06a8c3dad5304476b0f9333ef43c252cb989b0cfbe6460341aac353b","sha256:f87e7d0976984aef228829be0fd4ce0f1adc543a76e2619e0a2f59605d996246"],"state_sha256":"59ea37a4f4ebdc63b7f9869557134848b92fdd4699475654d632f0136050e260"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yft+ywqn7+lLvSgSYVrPMgwthIs9ahgUgsteyGZrn2qqV5G7L501oHEKxMvJUEe/86PvKVu21IvhDbL0AMOKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:42:40.068748Z","bundle_sha256":"589dce491d46d09d4b8be77986f0289d51c4e22caa494c47691d473d6d44dde2"}}