{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2GL5ZIRCOT23YMDGGMUXC3MHWL","short_pith_number":"pith:2GL5ZIRC","schema_version":"1.0","canonical_sha256":"d197dca22274f5bc30663329716d87b2cf61e3696a672d30cddf29259b5259ed","source":{"kind":"arxiv","id":"2012.00732","version":1},"attestation_state":"computed","paper":{"title":"Convergence and Sample Complexity of SGD in GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Christos Tzamos, Sihan Liu, Vasilis Kontonis","submitted_at":"2020-12-01T18:50:38Z","abstract_excerpt":"We provide theoretical convergence guarantees on training Generative Adversarial Networks (GANs) via SGD. We consider learning a target distribution modeled by a 1-layer Generator network with a non-linear activation function $\\phi(\\cdot)$ parametrized by a $d \\times d$ weight matrix $\\mathbf W_*$, i.e., $f_*(\\mathbf x) = \\phi(\\mathbf W_* \\mathbf x)$.\n  Our main result is that by training the Generator together with a Discriminator according to the Stochastic Gradient Descent-Ascent iteration proposed by Goodfellow et al. yields a Generator distribution that approaches the target distribution "},"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":"2012.00732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-01T18:50:38Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"785c34a84b4e178547a3925b65b1d4fc094e84d5485b8f15d0d8ee64286009e2","abstract_canon_sha256":"ea4fe065cedd2bda55fd32b29f2bbe60fc9ba8db52683dd7109c5efa6469a9b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:19.350668Z","signature_b64":"PU/BLL1HK/gPyDbRiTe8MPaAHD2Keo3C5yFxXVsFUs03/lbklaUGTLGxvsysDiIRaLNGfwsFlmD4TIrI+trRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d197dca22274f5bc30663329716d87b2cf61e3696a672d30cddf29259b5259ed","last_reissued_at":"2026-07-05T01:56:19.350334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:19.350334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence and Sample Complexity of SGD in GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Christos Tzamos, Sihan Liu, Vasilis Kontonis","submitted_at":"2020-12-01T18:50:38Z","abstract_excerpt":"We provide theoretical convergence guarantees on training Generative Adversarial Networks (GANs) via SGD. We consider learning a target distribution modeled by a 1-layer Generator network with a non-linear activation function $\\phi(\\cdot)$ parametrized by a $d \\times d$ weight matrix $\\mathbf W_*$, i.e., $f_*(\\mathbf x) = \\phi(\\mathbf W_* \\mathbf x)$.\n  Our main result is that by training the Generator together with a Discriminator according to the Stochastic Gradient Descent-Ascent iteration proposed by Goodfellow et al. yields a Generator distribution that approaches the target distribution "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00732","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/2012.00732/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":"2012.00732","created_at":"2026-07-05T01:56:19.350390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.00732v1","created_at":"2026-07-05T01:56:19.350390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00732","created_at":"2026-07-05T01:56:19.350390+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GL5ZIRCOT23","created_at":"2026-07-05T01:56:19.350390+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GL5ZIRCOT23YMDG","created_at":"2026-07-05T01:56:19.350390+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GL5ZIRC","created_at":"2026-07-05T01:56:19.350390+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/2GL5ZIRCOT23YMDGGMUXC3MHWL","json":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL.json","graph_json":"https://pith.science/api/pith-number/2GL5ZIRCOT23YMDGGMUXC3MHWL/graph.json","events_json":"https://pith.science/api/pith-number/2GL5ZIRCOT23YMDGGMUXC3MHWL/events.json","paper":"https://pith.science/paper/2GL5ZIRC"},"agent_actions":{"view_html":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL","download_json":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL.json","view_paper":"https://pith.science/paper/2GL5ZIRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.00732&json=true","fetch_graph":"https://pith.science/api/pith-number/2GL5ZIRCOT23YMDGGMUXC3MHWL/graph.json","fetch_events":"https://pith.science/api/pith-number/2GL5ZIRCOT23YMDGGMUXC3MHWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL/action/storage_attestation","attest_author":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL/action/author_attestation","sign_citation":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL/action/citation_signature","submit_replication":"https://pith.science/pith/2GL5ZIRCOT23YMDGGMUXC3MHWL/action/replication_record"}},"created_at":"2026-07-05T01:56:19.350390+00:00","updated_at":"2026-07-05T01:56:19.350390+00:00"}