More Like this

1. Non-asymptotic Performance Guarantees for Neural Estimation of f-divergences

   Sreekumar, Sreejith; Zhang, Zhengxin; Goldfeld, Ziv (January 2022, Proceedings of Machine Learning Research)

   Statistical distances (SDs), which quantify the dissimilarity between probability distributions, are central to machine learning and statistics. A modern method for estimating such distances from data relies on parametrizing a variational form by a neural network (NN) and optimizing it. These estimators are abundantly used in practice, but corresponding performance guarantees are partial and call for further exploration. In particular, there seems to be a fundamental tradeoff between the two sources of error involved: approximation and estimation. While the former needs the NN class to be rich and expressive, the latter relies on controlling complexity. This paper explores this tradeoff by means of non-asymptotic error bounds, focusing on three popular choices of SDs—Kullback-Leibler divergence, chi-squared divergence, and squared Hellinger distance. Our analysis relies on non-asymptotic function approximation theorems and tools from empirical process theory. Numerical results validating the theory are also provided. 

   more » « less
2. Non-asymptotic Performance Guarantees for Neural Estimation of f-Divergences

   Sreejith Sreekumar, Zhengxin Zhang (January 2021, Proeedings of the International Workshop on Artificial Intelligence and Statistics)

   null (Ed.)

   Statistical distances (SDs), which quantify the dissimilarity between probability distri- butions, are central to machine learning and statistics. A modern method for esti- mating such distances from data relies on parametrizing a variational form by a neu- ral network (NN) and optimizing it. These estimators are abundantly used in prac- tice, but corresponding performance guar- antees are partial and call for further ex- ploration. In particular, there seems to be a fundamental tradeoff between the two sources of error involved: approximation and estimation. While the former needs the NN class to be rich and expressive, the latter relies on controlling complexity. This paper explores this tradeoff by means of non-asymptotic error bounds, focusing on three popular choices of SDs—Kullback- Leibler divergence, chi-squared divergence, and squared Hellinger distance. Our analysis relies on non-asymptotic function approxima- tion theorems and tools from empirical pro- cess theory. Numerical results validating the theory are also provided. 

   more » « less
3. Indirect inference for time series using the empirical characteristic function and control variates

   https://doi.org/10.1111/jtsa.12582  

   Davis, Richard A.; do Rêgo Sousa, Thiago; Klüppelberg, Claudia (January 2021, Journal of Time Series Analysis)

   null (Ed.)

   We estimate the parameter of a stationary time series process by minimizing the integrated weighted mean squared error between the empirical and simulated characteristic function, when the true characteristic functions cannot be explicitly computed. Motivated by Indirect Inference, we use a Monte Carlo approximation of the characteristic function based on i.i.d. simulated blocks. As a classical variance reduction technique, we propose the use of control variates for reducing the variance of this Monte Carlo approximation. These two approximations yield two new estimators that are applicable to a large class of time series processes. We show consistency and asymptotic normality of the parameter estimators under strong mixing, moment conditions, and smoothness of the simulated blocks with respect to its parameter. In a simulation study we show the good performance of these new simulation based estimators, and the superiority of the control variates based estimator for Poisson driven time series of counts 

   more » « less
4. Bayesian estimation of the Kullback-Leibler divergence for categorical systems using mixtures of Dirichlet priors

   https://doi.org/10.1103/PhysRevE.109.024305  

   Camaglia, Francesco; Nemenman, Ilya; Mora, Thierry; Walczak, Aleksandra M. (February 2024, Physical Review E)

   In many applications in biology, engineering, and economics, identifying similarities and differences between distributions of data from complex processes requires comparing finite categorical samples of discrete counts. Statistical divergences quantify the difference between two distributions. However, their estimation is very difficult and empirical methods often fail, especially when the samples are small. We develop a Bayesian estimator of the Kullback-Leibler divergence between two probability distributions that makes use of a mixture of Dirichlet priors on the distributions being compared. We study the properties of the estimator on two examples: probabilities drawn from Dirichlet distributions and random strings of letters drawn from Markov chains. We extend the approach to the squared Hellinger divergence. Both estimators outperform other estimation techniques, with better results for data with a large number of categories and for higher values of divergences. 

   more » « less
5. Consistency of empirical distributions of sequences of graph statistics in networks with dependent edges

   https://doi.org/10.1016/j.jmva.2025.105420  

   Stewart, Jonathan R (February 2025, Journal of Multivariate Analysis)

   One of the first steps in applications of statistical network analysis is frequently to produce summary charts of important features of the network. Many of these features take the form of sequences of graph statistics counting the number of realized events in the network, examples of which are degree distributions, edgewise shared partner distributions, and more. We provide conditions under which the empirical distributions of sequences of graph statistics are consistent in the L-infinity-norm in settings where edges in the network are dependent. We accomplish this task by deriving concentration inequalities that bound probabilities of deviations of graph statistics from the expected value under weak dependence conditions. We apply our concentration inequalities to empirical distributions of sequences of graph statistics and derive non-asymptotic bounds on the L-infinity-error which hold with high probability. Our non-asymptotic results are then extended to demonstrate uniform convergence almost surely in selected examples. We illustrate theoretical results through examples, simulation studies, and an application. 

   more » « less