**Local Reparameterization Network (LR-Nets)**

Recent breakthroughs in computer vision make use of large deep neural networks, utilizing the substantial speedup offered by GPUs. For applications running on limited hardware however, high precision real-time processing can still be a challenge. One approach to solve this problem is learning networks with binary or ternary weights, thus removing the need to calculate multiplications and significantly reduce memory size and access. In this work we introduce LR-nets (Local reparameterization networks), a new method for training neural networks with discrete weights using stochastic parameters. We show how a simple modification to the local reparameterization trick, previously used to train Gaussian distributed weights, allows us to train discrete weights. We tested our method on MNIST, CIFAR-10 and ImageNet, achieving state-of-the-art results compared to previous binary and ternary models. … **Random Weighting**

This paper provides an entire inference procedure for the autoregressive model under (conditional) heteroscedasticity of unknown form with a finite variance. We first establish the asymptotic normality of the weighted least absolute deviations estimator (LADE) for the model. Second, we develop the random weighting (RW) method to estimate its asymptotic covariance matrix, leading to the implementation of the Wald test. Third, we construct a portmanteau test for model checking, and use the RW method to obtain its critical values. As a special weighted LADE, the feasible adaptive LADE (ALADE) is proposed and proved to have the same efficiency as its infeasible counterpart. The importance of our entire methodology based on the feasible ALADE is illustrated by simulation results and the real data analysis on three U.S. economic data sets. … **Fair Regression**

In this paper, we study the prediction of a real-valued target, such as a risk score or recidivism rate, while guaranteeing a quantitative notion of fairness with respect to a protected attribute such as gender or race. We call this class of problems \emph{fair regression}. We propose general schemes for fair regression under two notions of fairness: (1) statistical parity, which asks that the prediction be statistically independent of the protected attribute, and (2) bounded group loss, which asks that the prediction error restricted to any protected group remain below some pre-determined level. While we only study these two notions of fairness, our schemes are applicable to arbitrary Lipschitz-continuous losses, and so they encompass least-squares regression, logistic regression, quantile regression, and many other tasks. Our schemes only require access to standard risk minimization algorithms (such as standard classification or least-squares regression) while providing theoretical guarantees on the optimality and fairness of the obtained solutions. In addition to analyzing theoretical properties of our schemes, we empirically demonstrate their ability to uncover fairness–accuracy frontiers on several standard datasets. … **Distributed Lance-William Clustering Algorithm**

One important tool is the optimal clustering of data into useful categories. Dividing similar objects into a smaller number of clusters is of importance in many applications. These include search engines, monitoring of academic performance, biology and wireless networks. We first discuss a number of clustering methods. We present a parallel algorithm for the efficient clustering of objects into groups based on their similarity to each other. The input consists of an n by n distance matrix. This matrix would have a distance ranking for each pair of objects. The smaller the number, the more similar the two objects are to each other. We utilize parallel processors to calculate a hierarchal cluster of these n items based on this matrix. Another advantage of our method is distribution of the large n by n matrix. We have implemented our algorithm and have found it to be scalable both in terms of processing speed and storage. …

# If you did not already know

**28**
*Tuesday*
Dec 2021

Posted What is ...

in