{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RC3XJGELY5ELN4Y5UBCE72EJ2I","short_pith_number":"pith:RC3XJGEL","canonical_record":{"source":{"id":"1708.02544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T16:15:26Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"826afbcf66cfef06a93fdba98a06239d1ff51da1105ab7f6e42dd2a82de8afce","abstract_canon_sha256":"3eb545f2d194b671a8817dbe9eacc6cc2110a109a911421e348ff853789baee8"},"schema_version":"1.0"},"canonical_sha256":"88b774988bc748b6f31da0444fe889d20a143c4d269cb99c7abaf8a2ddee446e","source":{"kind":"arxiv","id":"1708.02544","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02544","created_at":"2026-05-18T00:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02544v2","created_at":"2026-05-18T00:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02544","created_at":"2026-05-18T00:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"RC3XJGELY5EL","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RC3XJGELY5ELN4Y5","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RC3XJGEL","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RC3XJGELY5ELN4Y5UBCE72EJ2I","target":"record","payload":{"canonical_record":{"source":{"id":"1708.02544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T16:15:26Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"826afbcf66cfef06a93fdba98a06239d1ff51da1105ab7f6e42dd2a82de8afce","abstract_canon_sha256":"3eb545f2d194b671a8817dbe9eacc6cc2110a109a911421e348ff853789baee8"},"schema_version":"1.0"},"canonical_sha256":"88b774988bc748b6f31da0444fe889d20a143c4d269cb99c7abaf8a2ddee446e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:20.274865Z","signature_b64":"uidoQ4BMWOM4MVBEaJAc09/912vMTJrqj5uxWqPDk4J4tINQ0563WFf+Sy5b4AwZcv9Ay2NzV0u6PUMK3p+CDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88b774988bc748b6f31da0444fe889d20a143c4d269cb99c7abaf8a2ddee446e","last_reissued_at":"2026-05-18T00:38:20.274213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:20.274213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.02544","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OXPsF1EulGVFOpSpqFW25FsREBZ4O6AS/BMzW4u3H8XvF/bNFr+lAx513BBm0WVVbeJTOXUthnImkmLm5ukkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:23:29.315493Z"},"content_sha256":"6cc936aaa6bd0c15762baee42c56c0bde384050bb90ae4ad283f3fdb85062f22","schema_version":"1.0","event_id":"sha256:6cc936aaa6bd0c15762baee42c56c0bde384050bb90ae4ad283f3fdb85062f22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RC3XJGELY5ELN4Y5UBCE72EJ2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Optimization with Bandit Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Farnood Salehi, L. Elisa Celis, Patrick Thiran","submitted_at":"2017-08-08T16:15:26Z","abstract_excerpt":"Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the estimator might have a large variance, which inadvertently slows down the convergence rate of the algorithms. One way to reduce this variance is to sample the datapoints from a carefully selected non-uniform distribution. In this work, we propose a novel non-uniform sampling approach that uses the multi-armed bandit framework. Theoretically, we show that our algorithm asymptotically approximates the optimal variance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02544","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":""},"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":"2026-05-18T00:38:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0dcQ4+tTRTfdCw0VOiUjNJUvnYfwSg3bJ+tPD7ANHelKgvRTRR1sgzMUMDASAZ8X4gt6WMRwXQKUBQrld6tqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T00:23:29.316186Z"},"content_sha256":"d1de5445637aff9e83c71efa4df2e256753f3e8368e70c6f988f06eb8a0250e1","schema_version":"1.0","event_id":"sha256:d1de5445637aff9e83c71efa4df2e256753f3e8368e70c6f988f06eb8a0250e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RC3XJGELY5ELN4Y5UBCE72EJ2I/bundle.json","state_url":"https://pith.science/pith/RC3XJGELY5ELN4Y5UBCE72EJ2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RC3XJGELY5ELN4Y5UBCE72EJ2I/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":"2026-05-24T00:23:29Z","links":{"resolver":"https://pith.science/pith/RC3XJGELY5ELN4Y5UBCE72EJ2I","bundle":"https://pith.science/pith/RC3XJGELY5ELN4Y5UBCE72EJ2I/bundle.json","state":"https://pith.science/pith/RC3XJGELY5ELN4Y5UBCE72EJ2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RC3XJGELY5ELN4Y5UBCE72EJ2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RC3XJGELY5ELN4Y5UBCE72EJ2I","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":"3eb545f2d194b671a8817dbe9eacc6cc2110a109a911421e348ff853789baee8","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T16:15:26Z","title_canon_sha256":"826afbcf66cfef06a93fdba98a06239d1ff51da1105ab7f6e42dd2a82de8afce"},"schema_version":"1.0","source":{"id":"1708.02544","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02544","created_at":"2026-05-18T00:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02544v2","created_at":"2026-05-18T00:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02544","created_at":"2026-05-18T00:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"RC3XJGELY5EL","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RC3XJGELY5ELN4Y5","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RC3XJGEL","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:d1de5445637aff9e83c71efa4df2e256753f3e8368e70c6f988f06eb8a0250e1","target":"graph","created_at":"2026-05-18T00:38:20Z","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":"Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the estimator might have a large variance, which inadvertently slows down the convergence rate of the algorithms. One way to reduce this variance is to sample the datapoints from a carefully selected non-uniform distribution. In this work, we propose a novel non-uniform sampling approach that uses the multi-armed bandit framework. Theoretically, we show that our algorithm asymptotically approximates the optimal variance","authors_text":"Farnood Salehi, L. Elisa Celis, Patrick Thiran","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T16:15:26Z","title":"Stochastic Optimization with Bandit Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02544","kind":"arxiv","version":2},"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":"sha256:6cc936aaa6bd0c15762baee42c56c0bde384050bb90ae4ad283f3fdb85062f22","target":"record","created_at":"2026-05-18T00:38:20Z","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":"3eb545f2d194b671a8817dbe9eacc6cc2110a109a911421e348ff853789baee8","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T16:15:26Z","title_canon_sha256":"826afbcf66cfef06a93fdba98a06239d1ff51da1105ab7f6e42dd2a82de8afce"},"schema_version":"1.0","source":{"id":"1708.02544","kind":"arxiv","version":2}},"canonical_sha256":"88b774988bc748b6f31da0444fe889d20a143c4d269cb99c7abaf8a2ddee446e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88b774988bc748b6f31da0444fe889d20a143c4d269cb99c7abaf8a2ddee446e","first_computed_at":"2026-05-18T00:38:20.274213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:20.274213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uidoQ4BMWOM4MVBEaJAc09/912vMTJrqj5uxWqPDk4J4tINQ0563WFf+Sy5b4AwZcv9Ay2NzV0u6PUMK3p+CDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:20.274865Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.02544","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cc936aaa6bd0c15762baee42c56c0bde384050bb90ae4ad283f3fdb85062f22","sha256:d1de5445637aff9e83c71efa4df2e256753f3e8368e70c6f988f06eb8a0250e1"],"state_sha256":"487399e7cc9c40bca89b658db30b7edd1609d05f07d706cb5ded9ec356cfb7a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4D2aG96UvRkQNQKbVk/uVYAw7lZi5Wj9fFap5j+9U7umhFNkCjL3sFG3dBTputv6iiHYSzOsfvbvYeYTwnq8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T00:23:29.320675Z","bundle_sha256":"69b9474fdcea4f69d28622c97bc856ece076269d21408b070a4a313039d9bc19"}}