Identifiability of deep generative models without auxiliary information
We prove identifiability of a broad class of deep latent variable models that (a) have
universal approximation capabilities and (b) are the decoders of variational autoencoders …
universal approximation capabilities and (b) are the decoders of variational autoencoders …
Learning latent causal graphs via mixture oracles
We study the problem of reconstructing a causal graphical model from data in the presence
of latent variables. The main problem of interest is recovering the causal structure over the …
of latent variables. The main problem of interest is recovering the causal structure over the …
Unsupervised learning under latent label shift
What sorts of structure might enable a learner to discover classes from unlabeled data?
Traditional approaches rely on feature-space similarity and heroic assumptions on the data …
Traditional approaches rely on feature-space similarity and heroic assumptions on the data …
Source identification for mixtures of product distributions
We give an algorithm for source identification of a mixture of k product distributions on n bits.
This is a fundamental problem in machine learning with many applications. Our algorithm …
This is a fundamental problem in machine learning with many applications. Our algorithm …
MixTwice: large-scale hypothesis testing for peptide arrays by variance mixing
Peptide microarrays have emerged as a powerful technology in immunoproteomics as they
provide a tool to measure the abundance of different antibodies in patient serum samples …
provide a tool to measure the abundance of different antibodies in patient serum samples …
Uniform consistency in nonparametric mixture models
B Aragam, R Yang - The Annals of Statistics, 2023 - projecteuclid.org
Uniform consistency in nonparametric mixture models Page 1 The Annals of Statistics 2023,
Vol. 51, No. 1, 362–390 https://doi.org/10.1214/22-AOS2255 © Institute of Mathematical …
Vol. 51, No. 1, 362–390 https://doi.org/10.1214/22-AOS2255 © Institute of Mathematical …
Beyond smoothness: Incorporating low-rank analysis into nonparametric density estimation
RA Vandermeulen, A Ledent - Advances in Neural …, 2021 - proceedings.neurips.cc
The construction and theoretical analysis of the most popular universally consistent
nonparametric density estimators hinge on one functional property: smoothness. In this …
nonparametric density estimators hinge on one functional property: smoothness. In this …
Sample complexity using infinite multiview models
RA Vandermeulen - arXiv preprint arXiv:2302.04292, 2023 - arxiv.org
Recent works have demonstrated that the convergence rate of a nonparametric density
estimator can be greatly improved by using a low-rank estimator when the target density is a …
estimator can be greatly improved by using a low-rank estimator when the target density is a …
Convergence of de Finetti's mixing measure in latent structure models for observed exchangeable sequences
Due to space constraints, additional results are given in [38], which contains new tools from
harmonic analysis to analyze examples in Section 5.3, the sharpness of the established …
harmonic analysis to analyze examples in Section 5.3, the sharpness of the established …
Generalized Identifiability Bounds for Mixture Models With Grouped Samples
RA Vandermeulen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recent work has shown that finite mixture models with components are identifiable, while
making no assumptions on the mixture components, so long as one has access to groups of …
making no assumptions on the mixture components, so long as one has access to groups of …