The plug-in estimator of the Wasserstein distance is known to be conservative, however its usefulness is severely limited when the distributions are similar as its bias does not decay to zero with the true Wasserstein distance. We propose a linear combination of plug-in estimators for the squared 2-Wasserstein distance with a reduced bias that decays to zero with the true distance. The new estimator is provably conservative provided one distribution is appropriately overdispersed with respect the other, and is unbiased when the distributions are equal. We apply it to approximately bound from above the 2-Wasserstein distance between the target and current distribution in Markov chain Monte Carlo, running multiple identically distributed chains which start, and remain, overdispersed with respect to the target. Our bound consistently outperforms the current state-of-the-art bound, which uses coupling, improving mixing time bounds by up to an order of magnitude.

Mathematics is the core of all machine learning algorithms. And while it isn't a prerequisite to have formal math education in order to become a data scientist, you need to understand the principles of the subject well enough to successfully build models that add value. In an article I wrote previously, I explained the three branches of mathematics that were essential to gain a deeper understanding of ML algorithms -- statistics, calculus, and linear algebra. This article will solely focus on linear algebra, as it forms the backbone of machine learning model implementation. Linear algebra concepts like vectorization allow for faster computation speeds, and are implemented in libraries like Pandas, Scipy, and Scikit-Learn.

The Common mistake by a data scientist is Applying the tools without the intuition of how it works and behaves. Having the solid foundation of mathematics will help you to understand how each algorithm work, its limitations and its underlying assumptions. With this, you will have an edge over your peers and makes you more confident in all the applications of Machine Learning, Data Science, and Deep Learning. It always pays to know the machinery under the hood, rather than being a guy who is just behind the wheel with no knowledge about the car. Linear Algebra is one of the areas where everyone agrees to be a starting point in the learning curve of Machine Learning, Data Science, and Deep Learning.. Its basic elements – Vectors and Matrices are where we store our data for input as well as output.

This paper studies the problem of matching two complete graphs with edge weights correlated through latent geometries, extending a recent line of research on random graph matching with independent edge weights to geometric models. Specifically, given a random permutation $\pi^*$ on $[n]$ and $n$ iid pairs of correlated Gaussian vectors $\{X_{\pi^*(i)}, Y_i\}$ in $\mathbb{R}^d$ with noise parameter $\sigma$, the edge weights are given by $A_{ij}=\kappa(X_i,X_j)$ and $B_{ij}=\kappa(Y_i,Y_j)$ for some link function $\kappa$. The goal is to recover the hidden vertex correspondence $\pi^*$ based on the observation of $A$ and $B$. We focus on the dot-product model with $\kappa(x,y)=\langle x, y \rangle$ and Euclidean distance model with $\kappa(x,y)=\|x-y\|^2$, in the low-dimensional regime of $d=o(\log n)$ wherein the underlying geometric structures are most evident. We derive an approximate maximum likelihood estimator, which provably achieves, with high probability, perfect recovery of $\pi^*$ when $\sigma=o(n^{-2/d})$ and almost perfect recovery with a vanishing fraction of errors when $\sigma=o(n^{-1/d})$. Furthermore, these conditions are shown to be information-theoretically optimal even when the latent coordinates $\{X_i\}$ and $\{Y_i\}$ are observed, complementing the recent results of [DCK19] and [KNW22] in geometric models of the planted bipartite matching problem. As a side discovery, we show that the celebrated spectral algorithm of [Ume88] emerges as a further approximation to the maximum likelihood in the geometric model.

Linear algebra operations, which are ubiquitous in machine learning, form major performance bottlenecks. The High-Performance Computing community invests significant effort in the development of architecture-specific optimized kernels, such as those provided by the BLAS and LAPACK libraries, to speed up linear algebra operations. However, end users are progressively less likely to go through the error prone and time-consuming process of directly using said kernels; instead, frameworks such as TensorFlow (TF) and PyTorch (PyT), which facilitate the development of machine learning applications, are becoming more and more popular. Although such frameworks link to BLAS and LAPACK, it is not clear whether or not they make use of linear algebra knowledge to speed up computations. For this reason, in this paper we develop benchmarks to investigate the linear algebra optimization capabilities of TF and PyT. Our analyses reveal that a number of linear algebra optimizations are still missing; for instance, reducing the number of scalar operations by applying the distributive law, and automatically identifying the optimal parenthesization of a matrix chain. In this work, we focus on linear algebra computations in TF and PyT; we both expose opportunities for performance enhancement to the benefit of the developers of the frameworks and provide end users with guidelines on how to achieve performance gains.

In the following image we can see an alternative basis for one coordinate system and those are basis vectors \(\vec{b}_{1} \) and \(\vec{b}_{2} \). On the other hand, in this different alternative coordinate system it is represented with coordinates \(-1 \) because that's how much we have to scale vector \(\vec{b}_{1} \) and it's scaled with \(2 \) along \(\vec{b}_{2} \), cause that's how we much we have to scale our \(\vec{b}_{2} \) vector.

Given a single trajectory of a dynamical system, we analyze the performance of the nonparametric least squares estimator (LSE). More precisely, we give nonasymptotic expected $l^2$-distance bounds between the LSE and the true regression function, where expectation is evaluated on a fresh, counterfactual, trajectory. We leverage recently developed information-theoretic methods to establish the optimality of the LSE for nonparametric hypotheses classes in terms of supremum norm metric entropy and a subgaussian parameter. Next, we relate this subgaussian parameter to the stability of the underlying process using notions from dynamical systems theory. When combined, these developments lead to rate-optimal error bounds that scale as $T^{-1/(2+q)}$ for suitably stable processes and hypothesis classes with metric entropy growth of order $\delta^{-q}$. Here, $T$ is the length of the observed trajectory, $\delta \in \mathbb{R}_+$ is the packing granularity and $q\in (0,2)$ is a complexity term. Finally, we specialize our results to a number of scenarios of practical interest, such as Lipschitz dynamics, generalized linear models, and dynamics described by functions in certain classes of Reproducing Kernel Hilbert Spaces (RKHS).

In distributional reinforcement learning not only expected returns but the complete return distributions of a policy are taken into account. The return distribution for a fixed policy is given as the solution of an associated distributional Bellman equation. In this note we consider general distributional Bellman equations and study existence and uniqueness of their solutions as well as tail properties of return distributions. We give necessary and sufficient conditions for existence and uniqueness of return distributions and identify cases of regular variation. We link distributional Bellman equations to multivariate affine distributional equations. We show that any solution of a distributional Bellman equation can be obtained as the vector of marginal laws of a solution to a multivariate affine distributional equation. This makes the general theory of such equations applicable to the distributional reinforcement learning setting.

Welcome to Probability and Statistics for Business and Data Science! In this course we cover what you need to know about probability and statistics to succeed in business and the data science field! This practical course will go over theory and implementation of statistics to real world problems. Each section has example problems, in course quizzes, and assessment tests. We'll start by talking about the basics of data, understanding how to examine it with measurements of central tendency, dispersion, and also building an understanding of how bivariate data sources can relate to each other.

This post will be quite an interesting one. We will show how a 2D plane can be transformed into another one. Understanding these concepts is a crucial step for some more advanced linear algebra/machine learning methods (e.g. So, let's proceed and we will learn how to connect a matrix-vector multiplication with a linear transformation. In this post we will introduce a linear transformation. A linear transformation can also be seen as a simple function.