Matches in SemOpenAlex for { <https://semopenalex.org/work/W2982324875> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2982324875 abstract "Generative Adversarial Networks (GAN) have shown promising results on a wide variety of complex tasks. Recent experiments show adversarial training provides useful gradients to the generator that helps attain better performance. In this paper, we intend to theoretically analyze whether supervised learning with adversarial features can outperform sole supervision, or not. First, we show that supervised learning without adversarial features suffer from vanishing gradient issue in near optimal region. Second, we analyze how adversarial learning augmented with supervised signal mitigates this vanishing gradient issue. Finally, we prove our main result that shows supervised learning with adversarial features can be better than sole supervision (under some mild assumptions). We support our main result on two fronts (i) expected empirical risk and (ii) rate of convergence." @default.
- W2982324875 created "2019-11-08" @default.
- W2982324875 creator A5052553707 @default.
- W2982324875 date "2019-10-30" @default.
- W2982324875 modified "2023-09-27" @default.
- W2982324875 title "Is Supervised Learning With Adversarial Features Provably Better Than Sole Supervision" @default.
- W2982324875 cites W2099471712 @default.
- W2982324875 cites W2911583094 @default.
- W2982324875 cites W2962376003 @default.
- W2982324875 cites W2962793481 @default.
- W2982324875 cites W2963073614 @default.
- W2982324875 cites W2963446712 @default.
- W2982324875 cites W2963470893 @default.
- W2982324875 cites W2963881378 @default.
- W2982324875 cites W2964242925 @default.
- W2982324875 cites W3101639073 @default.
- W2982324875 hasPublicationYear "2019" @default.
- W2982324875 type Work @default.
- W2982324875 sameAs 2982324875 @default.
- W2982324875 citedByCount "0" @default.
- W2982324875 crossrefType "posted-content" @default.
- W2982324875 hasAuthorship W2982324875A5052553707 @default.
- W2982324875 hasConcept C119857082 @default.
- W2982324875 hasConcept C121332964 @default.
- W2982324875 hasConcept C136197465 @default.
- W2982324875 hasConcept C136389625 @default.
- W2982324875 hasConcept C154945302 @default.
- W2982324875 hasConcept C162324750 @default.
- W2982324875 hasConcept C163258240 @default.
- W2982324875 hasConcept C2777303404 @default.
- W2982324875 hasConcept C2780992000 @default.
- W2982324875 hasConcept C37736160 @default.
- W2982324875 hasConcept C39890363 @default.
- W2982324875 hasConcept C41008148 @default.
- W2982324875 hasConcept C50522688 @default.
- W2982324875 hasConcept C50644808 @default.
- W2982324875 hasConcept C62520636 @default.
- W2982324875 hasConceptScore W2982324875C119857082 @default.
- W2982324875 hasConceptScore W2982324875C121332964 @default.
- W2982324875 hasConceptScore W2982324875C136197465 @default.
- W2982324875 hasConceptScore W2982324875C136389625 @default.
- W2982324875 hasConceptScore W2982324875C154945302 @default.
- W2982324875 hasConceptScore W2982324875C162324750 @default.
- W2982324875 hasConceptScore W2982324875C163258240 @default.
- W2982324875 hasConceptScore W2982324875C2777303404 @default.
- W2982324875 hasConceptScore W2982324875C2780992000 @default.
- W2982324875 hasConceptScore W2982324875C37736160 @default.
- W2982324875 hasConceptScore W2982324875C39890363 @default.
- W2982324875 hasConceptScore W2982324875C41008148 @default.
- W2982324875 hasConceptScore W2982324875C50522688 @default.
- W2982324875 hasConceptScore W2982324875C50644808 @default.
- W2982324875 hasConceptScore W2982324875C62520636 @default.
- W2982324875 hasLocation W29823248751 @default.
- W2982324875 hasOpenAccess W2982324875 @default.
- W2982324875 hasPrimaryLocation W29823248751 @default.
- W2982324875 hasRelatedWork W2245869277 @default.
- W2982324875 hasRelatedWork W2573774505 @default.
- W2982324875 hasRelatedWork W2752660961 @default.
- W2982324875 hasRelatedWork W2884169041 @default.
- W2982324875 hasRelatedWork W2947563562 @default.
- W2982324875 hasRelatedWork W2963501948 @default.
- W2982324875 hasRelatedWork W2963783970 @default.
- W2982324875 hasRelatedWork W2982120826 @default.
- W2982324875 hasRelatedWork W2995645057 @default.
- W2982324875 hasRelatedWork W3003369812 @default.
- W2982324875 hasRelatedWork W3007712033 @default.
- W2982324875 hasRelatedWork W3008051686 @default.
- W2982324875 hasRelatedWork W3024886890 @default.
- W2982324875 hasRelatedWork W3028525609 @default.
- W2982324875 hasRelatedWork W3033258370 @default.
- W2982324875 hasRelatedWork W3039130562 @default.
- W2982324875 hasRelatedWork W3104032928 @default.
- W2982324875 hasRelatedWork W3130773951 @default.
- W2982324875 hasRelatedWork W3161366266 @default.
- W2982324875 hasRelatedWork W3176854876 @default.
- W2982324875 isParatext "false" @default.
- W2982324875 isRetracted "false" @default.
- W2982324875 magId "2982324875" @default.
- W2982324875 workType "article" @default.