{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QD72GXVZEXYO542TKF73URN2LP","short_pith_number":"pith:QD72GXVZ","schema_version":"1.0","canonical_sha256":"80ffa35eb925f0eef353517fba45ba5bd7064079c5c3f7adff99d103bb717be8","source":{"kind":"arxiv","id":"1808.00020","version":6},"attestation_state":"computed","paper":{"title":"On-line Adaptative Curriculum Learning for GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Audrey Durand, Bogdan Mazoure, Isabela Albuquerque, Joao Monteiro, Joelle Pineau, R Devon Hjelm, Thang Doan","submitted_at":"2018-07-31T18:34:56Z","abstract_excerpt":"Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open questions such as sufficient convergence conditions and mode collapse still persist. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting. We formalize this problem within the full-information adversarial bandit framework, where we evaluate the capability of an algorithm to select mixtures of "},"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":"1808.00020","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-31T18:34:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3f61ecd4f2446ea2edbb17d8bd5f4f25a504933269cc982681739841478807ca","abstract_canon_sha256":"2c01c88ecf20a54a0d87eca625c7db126cb7c40b86ff33612a678f21bd5d2149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:33.493544Z","signature_b64":"O/VkWBduQtoLM6+cK6Oj/SmvTaAOCJueBfbMu/MFXLtSwn3YzUBNuTD+Vt/SS2nGSXFwyCGdPwouYm6O6eoWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80ffa35eb925f0eef353517fba45ba5bd7064079c5c3f7adff99d103bb717be8","last_reissued_at":"2026-05-17T23:51:33.492856Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:33.492856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-line Adaptative Curriculum Learning for GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Audrey Durand, Bogdan Mazoure, Isabela Albuquerque, Joao Monteiro, Joelle Pineau, R Devon Hjelm, Thang Doan","submitted_at":"2018-07-31T18:34:56Z","abstract_excerpt":"Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open questions such as sufficient convergence conditions and mode collapse still persist. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting. We formalize this problem within the full-information adversarial bandit framework, where we evaluate the capability of an algorithm to select mixtures of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00020","kind":"arxiv","version":6},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1808.00020","created_at":"2026-05-17T23:51:33.492975+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.00020v6","created_at":"2026-05-17T23:51:33.492975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00020","created_at":"2026-05-17T23:51:33.492975+00:00"},{"alias_kind":"pith_short_12","alias_value":"QD72GXVZEXYO","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QD72GXVZEXYO542T","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QD72GXVZ","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP","json":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP.json","graph_json":"https://pith.science/api/pith-number/QD72GXVZEXYO542TKF73URN2LP/graph.json","events_json":"https://pith.science/api/pith-number/QD72GXVZEXYO542TKF73URN2LP/events.json","paper":"https://pith.science/paper/QD72GXVZ"},"agent_actions":{"view_html":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP","download_json":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP.json","view_paper":"https://pith.science/paper/QD72GXVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.00020&json=true","fetch_graph":"https://pith.science/api/pith-number/QD72GXVZEXYO542TKF73URN2LP/graph.json","fetch_events":"https://pith.science/api/pith-number/QD72GXVZEXYO542TKF73URN2LP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP/action/storage_attestation","attest_author":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP/action/author_attestation","sign_citation":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP/action/citation_signature","submit_replication":"https://pith.science/pith/QD72GXVZEXYO542TKF73URN2LP/action/replication_record"}},"created_at":"2026-05-17T23:51:33.492975+00:00","updated_at":"2026-05-17T23:51:33.492975+00:00"}