We exhibit examples of high-dimensional unimodal posterior distributions arising in non-linear regression models with Gaussian process priors for which MCMC methods can take an exponential run-time to enter the regions where the bulk of the posterior measure concentrates. Our results apply to worst-case initialised (`cold start') algorithms that are local in the sense that their step-sizes cannot be too large on average. The counter-examples hold for general MCMC schemes based on gradient or random walk steps, and the theory is illustrated for Metropolis-Hastings adjusted methods such as pCN and MALA.
The aim of this work is the comparison of the performance of the three popular software platforms JAGS, NIMBLE and Stan. These probabilistic programming languages are able to automatically generate samples from the posterior distribution of interest using MCMC algorithms, starting from the specification of a Bayesian model, i.e. the likelihood and the prior. The final goal is to present a detailed analysis of their strengths and weaknesses to statisticians or applied scientists. In this way, we wish to contribute to make them fully aware of the pros and cons of this software. We carry out a sy…
The purpose of this research is to develop an MCMC algorithm for estimating the Q-matrix. Based on the DINA model, the algorithm starts with estimating correlated attributes. Using a saturated model and a binary decimal conversion, the algorithm transforms possible attribute patterns to a Multinomial distribution. Along with the likelihood of an attribute pattern, a Dirichlet distribution, constructed using Gamma distributions, is used as the prior to sample from the posterior. Correlated attributes of examinees are generated using inverse transform sampling. Closed form posteriors for samplin…
University of South Carolina（南卡罗来纳大学）；University of North Carolina Charlotte（北卡罗来纳大学夏洛特分校）
Markov Chain Monte Carlo (MCMC) methods have a drawback when working with a target distribution or likelihood function that is computationally expensive to evaluate, specially when working with big data. This paper focuses on Metropolis-Hastings (MH) algorithm for unimodal distributions. Here, an enhanced MH algorithm is proposed that requires less number of expensive function evaluations, has shorter burn-in period, and uses a better proposal distribution. The main innovations include the use of Bayesian optimization to reach the high probability region quickly, emulating the target distribut…
University of Cambridge（剑桥大学）；Microsoft Research（微软研究院）
In this paper we introduce the ice-start problem, i.e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquiring each feature element of data is associated with costs. This setting is representative for the real-world machine learning applications. For instance, in the health-care domain, when training an AI system for predicting patient metrics from lab tests, obtaining every single measurement comes with a high cost. Active learning, where only the label is associated with a cost does not apply to such problem, because perf…
Articles in Marketing and choice literatures have demonstrated the need for incorporating person-level heterogeneity into behavioral models (e.g., logit models for multiple binary outcomes as studied here). However, the logit likelihood extended with a population distribution of heterogeneity doesn't yield closed-form inferences, and therefore numerical integration techniques are relied upon (e.g., MCMC methods). We present here an alternative, closed-form Bayesian inferences for the logit model, which we obtain by approximating the logit likelihood via a polynomial expansion, and then positin…
Federated learning is typically approached as an optimization problem, where the goal is to minimize a global loss function by distributing computation across client devices that possess local data and specify different parts of the global objective. We present an alternative perspective and formulate federated learning as a posterior inference problem, where the goal is to infer a global posterior distribution by having client devices each infer the posterior of their local data. While exact inference is often intractable, this perspective provides a principled way to search for global optima…
In the standard Bayesian framework data are assumed to be generated by a distribution parametrized by $θ$ in a parameter space $Θ$, over which a prior distribution $π$ is given. A Bayesian statistician quantifies the belief that the true parameter is $θ_{0}$ in $Θ$ by its posterior probability given the observed data. We investigate the behavior of the posterior belief in $θ_{0}$ when the data are generated under some parameter $θ_{1},$ which may or may not be the same as $θ_{0}.$ Starting from stochastic orders, specifically, likelihood ratio dominance, that obtain for resulting distributions…
