Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. The book is written in an informal, accessible style, complete with pseudo-code for the most important algorithms. All topics are copiously illustrated with color images and worked examples drawn from such application domains as biology, text processing, computer vision, and robotics. Rather than providing a cookbook of different heuristic methods, the book stresses a principled model-based approach, often using the language of graphical models to specify models in a concise and intuitive way. Almost all the models described have been implemented in a MATLAB software package--PMTK (probabilistic modeling toolkit)--that is freely available online. The book is suitable for upper-level undergraduates with an introductory-level college math background and beginning graduate students.

Machine Learning : A Probabilistic Perspective

Statistics for Spatial Data.

/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

Most common human traits and diseases have a polygenic pattern of inheritance: DNA sequence variants at many genetic loci influence the phenotype. Genome-wide association (GWA) studies have identified more than 600 variants associated with human traits, but these typically explain small fractions of phenotypic variation, raising questions about the use of further studies. Here, using 183,727 individuals, we show that hundreds of genetic variants, in at least 180 loci, influence adult height, a highly heritable and classic polygenic trait. The large number of loci reveals patterns with important implications for genetic studies of common human diseases and traits. First, the 180 loci are not random, but instead are enriched for genes that are connected in biological pathways (P = 0.016) and that underlie skeletal growth defects (P < 0.001). Second, the likely causal gene is often located near the most strongly associated variant: in 13 of 21 loci containing a known skeletal growth gene, that gene was closest to the associated variant. Third, at least 19 loci have multiple independently associated variants, suggesting that allelic heterogeneity is a frequent feature of polygenic traits, that comprehensive explorations of already-discovered loci should discover additional variants and that an appreciable fraction of associated loci may have been identified. Fourth, associated variants are enriched for likely functional effects on genes, being over-represented among variants that alter amino-acid structure of proteins and expression levels of nearby genes. Our data explain approximately 10% of the phenotypic variation in height, and we estimate that unidentified common variants of similar effect sizes would increase this figure to approximately 16% of phenotypic variation (approximately 20% of heritable variation). Although additional approaches are needed to dissect the genetic architecture of polygenic human traits fully, our findings indicate that GWA studies can identify large numbers of loci that implicate biologically relevant genes and pathways.

Hundreds of variants clustered in genomic loci and biological pathways affect human height

We report on gravitational wave discoveries from compact binary coalescences detected by Advanced LIGO and Advanced Virgo in the first half of the third observing run (O3a) between 1 April 2019 15:00 UTC and 1 October 2019 15:00. By imposing a false-alarm-rate threshold of two per year in each of the four search pipelines that constitute our search, we present 39 candidate gravitational wave events. At this threshold, we expect a contamination fraction of less than 10%. Of these, 26 candidate events were reported previously in near real-time through GCN Notices and Circulars; 13 are reported here for the first time. The catalog contains events whose sources are black hole binary mergers up to a redshift of ~0.8, as well as events whose components could not be unambiguously identified as black holes or neutron stars. For the latter group, we are unable to determine the nature based on estimates of the component masses and spins from gravitational wave data alone. The range of candidate events which are unambiguously identified as binary black holes (both objects $\geq 3~M_\odot$) is increased compared to GWTC-1, with total masses from $\sim 14~M_\odot$ for GW190924_021846 to $\sim 150~M_\odot$ for GW190521. For the first time, this catalog includes binary systems with significantly asymmetric mass ratios, which had not been observed in data taken before April 2019. We also find that 11 of the 39 events detected since April 2019 have positive effective inspiral spins under our default prior (at 90% credibility), while none exhibit negative effective inspiral spin. Given the increased sensitivity of Advanced LIGO and Advanced Virgo, the detection of 39 candidate events in ~26 weeks of data (~1.5 per week) is consistent with GWTC-1.

GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run

A 3D numerical model is developed to simulate melting in packed bed encapsulated phase change material (PCM) energy storage systems. The main novelty of the model is that it resolves the arrangement of capsules inside the system for both structured and unstructured packing and thus accurately captures the fluid flow, heat transfer and phase change in the capsules. To create the unstructured arrangement of capsules in the domain a novel dropping and rolling algorithm is implemented. The flow of heat transfer fluid (HTF) outside the capsules as well as the natural convection in the PCM within the capsules is also simulated. Initially, a single capsule study is performed, which shows that both natural convection inside the liquid PCM and forced convection outside the capsule affect the melting characteristics. Subsequently, the model is extended to simulate phase change in multiple capsules in a cubical domain arranged with structured and unstructured packing. The analysis of the effect of capsule arrangement on the melting and energy storage characteristics for both structured and unstructured packing of capsules is performed. Additionally, parametric studies are performed to analyze the effects of capsule size, fluid temperature, and fluid velocity for both types of systems. Simulation results show that the total melting time for unstructured packing is reduced on an average by 23.56% for the 2.5 mm capsules and by 10.14% for the 5 mm capsules as compared to structured packing. The effect of HTF temperature change is more prominent for structured cases, with an increase of 65.8% melting time as compared to 58.4% for the unstructured cases when the HTF temperature is reduced by 20 K. In contrast, the effect of velocity is less significant for the structured cases with a reduction of HTF velocity from 0.1 cm/s to 0.05 cm/s causing an increase of 27.3% melting time for the structured cases and 42.6% for the unstructured cases. The developed model can be used to capture the effect of different arrangements of capsules in encapsulated PCM energy storage systems and thus obtain effective designs for such systems. 

A 3D resolved-geometry model for unstructured and structured packed bed encapsulated phase change material system

This paper studies the probabilistic hosting capacity analysis (PHCA) problem in distribution networks considering uncertainties from distributed energy resources (DERs) and residential loads. PHCA aims to compute the hosting capacity, which is defined as the maximal level of DERs that can be securely integrated into a distribution network while satisfying operational constraints with high probability. We formulate PHCA as a chance-constrained optimization problem, and model the uncertainties from DERs and loads using historical data. Due to non-convexities and a substantial number of historical scenarios being used, PHCA is often formulated as large-scale nonlinear optimization problem, thus computationally intractable to solve. To address the core computational challenges, we propose a fast and extensible framework to solve PHCA based on Bayesian Optimization (BayesOpt). Comparing with state-of-the-art algorithms such as interior point and active set, numerical results show that the proposed BayesOpt approach is able to find better solutions (25% higher hosting capacity) with 70% savings in computation time on average.

Probabilistic Hosting Capacity Analysis via Bayesian Optimization.

With the advent of structured data in the form of social networks, genetic circuits and protein interaction networks, statistical analysis of networks has gained popularity over recent years. The stochastic block model constitutes a classical cluster-exhibiting random graph model for networks. There is a substantial amount of literature devoted to proposing strategies for estimating and inferring parameters of the model, both from classical and Bayesian viewpoints. Unlike the classical counterpart, there is a dearth of theoretical results on the accuracy of estimation in the Bayesian setting. In this article, we undertake a theoretical investigation of the posterior distribution of the parameters in a stochastic block model. In particular, we show that one obtains near-optimal rates of posterior contraction with routinely used multinomial-Dirichlet priors on cluster indicators and uniform or general Beta priors on the probabilities of the random edge indicators. Our theoretical results are corroborated through a small scale simulation study.

Posterior Contraction Rates for Stochastic Block Models

We study posterior rates of contraction in Gaussian process regression with unbounded covariate domain. Our argument relies on developing a Gaussian approximation to the posterior of the leading coefficients of a Karhunen--Lo\'{e}ve expansion of the Gaussian process. The salient feature of our result is deriving such an approximation in the $L^2$ Wasserstein distance and relating the speed of the approximation to the posterior contraction rate using a coupling argument. Specific illustrations are provided for the Gaussian or squared-exponential covariance kernel.

Posterior contraction in Gaussian process regression using Wasserstein approximations

Non-linear latent variable models have become increasingly popular in a variety of applications. However, there has been little study on theoretical properties of these models. In this article, we study rates of posterior contraction in univariate density estimation for a class of non-linear latent variable models where unobserved U(0,1) latent variables are related to the response variables via a random non-linear regression with an additive error. Our approach relies on characterizing the space of densities induced by the above model as kernel convolutions with a general class of continuous mixing measures. The literature on posterior rates of contraction in density estimation almost entirely focuses on finite or countably infinite mixture models. We develop approximation results for our class of continuous mixing measures. Using an appropriate Gaussian process prior on the unknown regression function, we obtain the optimal frequentist rate up to a logarithmic factor under standard regularity conditions on the true density.

Anirban Bhattacharya

Papers

A 3D resolved-geometry model for unstructured and structured packed bed encapsulated phase change material system

Probabilistic Hosting Capacity Analysis via Bayesian Optimization.

Posterior Contraction Rates for Stochastic Block Models

Posterior contraction in Gaussian process regression using Wasserstein approximations

Posterior convergence rates in non-linear latent variable models