Learning Entangled Single-Sample Gaussians in the Subset-of-Signals Model

In the setting of entangled single-sample distributions, the goal is to estimate some common parameter shared by a family of $n$ distributions, given one single sample from each distribution. This paper studies mean estimation for entangled single-sample Gaussians that have a common mean but different unknown variances. We propose the subset-of-signals model where an unknown subset of $m$ variances are bounded by 1 while there are no assumptions on the other variances. In this model, we analyze a simple and natural method based on iteratively averaging the truncated samples, and show that the method achieves error $O \left(\frac{\sqrt{n\ln n}}{m}\right)$ with high probability when $m=\Omega(\sqrt{n\ln n})$, matching existing bounds for this range of $m$. We further prove lower bounds, showing that the error is $\Omega\left(\left(\frac{n}{m^4}\right)^{1/2}\right)$ when $m$ is between $\Omega(\ln n)$ and $O(n^{1/4})$, and the error is $\Omega\left(\left(\frac{n}{m^4}\right)^{1/6}\right)$ when $m$ is between $\Omega(n^{1/4})$ and $O(n^{1 - \epsilon})$ for an arbitrarily small $\epsilon>0$, improving existing lower bounds and extending to a wider range of $m$.

[1]  Roman Vershynin,et al.  High-Dimensional Probability , 2018 .

[2]  Santosh S. Vempala,et al.  The Spectral Method for General Mixture Models , 2008, SIAM J. Comput..

[3]  Mikhail Belkin,et al.  Polynomial Learning of Distribution Families , 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.

[4]  B Rosner,et al.  Regression analysis in the presence of heterogeneous intraclass correlations. , 1986, Biometrics.

[5]  Mikhail Belkin,et al.  Toward Learning Gaussian Mixtures with Arbitrary Separation , 2010, COLT.

[6]  Maurizio Vichi,et al.  Multivariate linear regression for heterogeneous data , 2013 .

[7]  Ankur Moitra,et al.  Settling the Polynomial Learnability of Mixtures of Gaussians , 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.

[8]  Sanjeev Arora,et al.  Learning mixtures of arbitrary gaussians , 2001, STOC '01.

[9]  Jeffrey A. Fessler,et al.  Asymptotic performance of PCA for high-dimensional heteroscedastic data , 2017, J. Multivar. Anal..

[10]  Jeffrey A. Fessler,et al.  Optimally Weighted PCA for High-Dimensional Heteroscedastic Data , 2018, SIAM Journal on Mathematics of Data Science.

[11]  Leslie G. Valiant,et al.  Learning Disjunction of Conjunctions , 1985, IJCAI.

[12]  Yingyu Liang,et al.  Learning Entangled Single-Sample Distributions via Iterative Trimming , 2020, AISTATS.

[13]  Anru R. Zhang,et al.  Heteroskedastic PCA: Algorithm, optimality, and applications , 2018, The Annals of Statistics.

[14]  Jerry Li,et al.  Being Robust (in High Dimensions) Can Be Practical , 2017, ICML.

[15]  Sanjoy Dasgupta,et al.  Learning mixtures of Gaussians , 1999, 40th Annual Symposium on Foundations of Computer Science (Cat. No.99CB37039).

[16]  Dimitris Achlioptas,et al.  On Spectral Learning of Mixtures of Distributions , 2005, COLT.

[17]  Yu Cheng,et al.  High-Dimensional Robust Mean Estimation in Nearly-Linear Time , 2018, SODA.

[18]  Adam Tauman Kalai,et al.  Efficiently learning mixtures of two Gaussians , 2010, STOC '10.

[19]  Jerry Li,et al.  Robustly Learning a Gaussian: Getting Optimal Error, Efficiently , 2017, SODA.

[20]  Daniel M. Kane,et al.  Robust Estimators in High Dimensions without the Computational Intractability , 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

[21]  Varun Jog,et al.  Estimating location parameters in entangled single-sample distributions , 2019, ArXiv.