Identifiability of deep generative models without auxiliary information

B Kivva, G Rajendran, P Ravikumar… - Advances in Neural …, 2022 - proceedings.neurips.cc
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 …

Learning latent causal graphs via mixture oracles

B Kivva, G Rajendran, P Ravikumar… - Advances in Neural …, 2021 - proceedings.neurips.cc
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 …

Unsupervised learning under latent label shift

M Roberts, P Mani, S Garg… - Advances in Neural …, 2022 - proceedings.neurips.cc
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 …

Source identification for mixtures of product distributions

S Gordon, BH Mazaheri, Y Rabani… - … on Learning Theory, 2021 - proceedings.mlr.press
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 …

MixTwice: large-scale hypothesis testing for peptide arrays by variance mixing

Z Zheng, AM Mergaert, IM Ong, MA Shelef… - …, 2021 - academic.oup.com
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 …

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 …

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 …

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 …

Convergence of de Finetti's mixing measure in latent structure models for observed exchangeable sequences

Y Wei, XL Nguyen - The Annals of Statistics, 2022 - projecteuclid.org
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 …

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 …