Discovery of Single Independent Latent Variable

Uri Shaham, Jonathan Svirsky, Ori Katz, Ronen Talmon

نتاج البحث: فصل من :كتاب / تقرير / مؤتمرمنشور من مؤتمرمراجعة النظراء

ملخص

Latent variable discovery is a central problem in data analysis with a broad range of applications in applied science. In this work, we consider data given as an invertible mixture of two statistically independent components, and assume that one of the components is observed while the other is hidden. Our goal is to recover the hidden component. For this purpose, we propose an autoencoder equipped with a discriminator. Unlike the standard nonlinear ICA problem, which was shown to be non-identifiable, in the special case of ICA we consider here, we show that our approach can recover the component of interest up to entropy-preserving transformation. We demonstrate the performance of the proposed approach in several tasks, including image synthesis, voice cloning, and fetal ECG extraction.

اللغة الأصليةالإنجليزيّة
عنوان منشور المضيفAdvances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022
المحررونS. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh
رقم المعيار الدولي للكتب (الإلكتروني)9781713871088
حالة النشرنُشِر - 2022
الحدث36th Conference on Neural Information Processing Systems, NeurIPS 2022 - New Orleans, الولايات المتّحدة
المدة: ٢٨ نوفمبر ٢٠٢٢٩ ديسمبر ٢٠٢٢

سلسلة المنشورات

الاسمAdvances in Neural Information Processing Systems
مستوى الصوت35

!!Conference

!!Conference36th Conference on Neural Information Processing Systems, NeurIPS 2022
الدولة/الإقليمالولايات المتّحدة
المدينةNew Orleans
المدة٢٨/١١/٢٢٩/١٢/٢٢

All Science Journal Classification (ASJC) codes

  • !!Information Systems
  • !!Signal Processing
  • !!Computer Networks and Communications

بصمة

أدرس بدقة موضوعات البحث “Discovery of Single Independent Latent Variable'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا