Talent Search systems aim to recommend potential candidates who are a good match to the hiring needs of a recruiter expressed in terms of the recruiter's search query or job posting. Past work in this domain has focused on linear and nonlinear models which lack preference personalization in the user-level due to being trained only with globally collected recruiter activity data. In this paper, we propose an entity-personalized Talent Search model which utilizes a combination of generalized linear mixed (GLMix) models and gradient boosted decision tree (GBDT) models, and provides personalized talent recommendations using nonlinear tree interaction features generated by the GBDT. We also present the offline and online system architecture for the productionization of this hybrid model approach in our Talent Search systems. Finally, we provide offline and online experiment results benchmarking our entity-personalized model with tree interaction features, which demonstrate significant improvements in our precision metrics compared to globally trained non-personalized models.

Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates. Based on a simple intuition that the direction of centripetal acceleration of an object moving in uniform circular motion is toward the center of the circle, we present the Simultaneous Centripetal Acceleration (SCA) method and the Alternating Centripetal Acceleration (ACA) method to alleviate the cyclic behaviors. Under suitable conditions, gradient descent methods with either SCA or ACA are shown to be linearly convergent for bilinear games. Numerical experiments are conducted by applying ACA to existing gradient-based algorithms in a GAN setup scenario, which demonstrate the superiority of ACA.

A novel machine learning optimization process coined Restrictive Federated Model Selection (RFMS) is proposed under the scenario, for example, when data from healthcare units can not leave the site it is situated on and it is forbidden to carry out training algorithms on remote data sites due to either technical or privacy and trust concerns. To carry out a clinical research under this scenario, an analyst could train a machine learning model only on local data site, but it is still possible to execute a statistical query at a certain cost in the form of sending a machine learning model to some of the remote data sites and get the performance measures as feedback, maybe due to prediction being usually much cheaper. Compared to federated learning, which is optimizing the model parameters directly by carrying out training across all data sites, RFMS trains model parameters only on one local data site but optimizes hyper-parameters across other data sites jointly since hyper-parameters play an important role in machine learning performance. The aim is to get a Pareto optimal model with respective to both local and remote unseen prediction losses, which could generalize well across data sites. In this work, we specifically consider high dimensional data with shifted distributions over data sites. As an initial investigation, Bayesian Optimization especially multi-objective Bayesian Optimization is used to guide an adaptive hyper-parameter optimization process to select models under the RFMS scenario. Empirical results show that solely using the local data site to tune hyper-parameters generalizes poorly across data sites, compared to methods that utilize the local and remote performances. Furthermore, in terms of dominated hypervolumes, multi-objective Bayesian Optimization algorithms show increased performance across multiple data sites among other candidates.

Many applications in Bayesian statistics are extremely computationally intensive. However, they are also often inherently parallel, making them prime targets for modern massively parallel central processing unit (CPU) architectures. While the use of multi-core and distributed computing is widely applied in the Bayesian community, very little attention has been given to fine-grain parallelisation using single instruction multiple data (SIMD) operations that are available on most modern commodity CPUs. Rather, most fine-grain tuning in the literature has centred around general purpose graphics processing units (GPGPUs). Since the effective utilisation of GPGPUs typically requires specialised programming languages, such technologies are not ideal for the wider Bayesian community. In this work, we practically demonstrate, using standard programming libraries, the utility of the SIMD approach for several topical Bayesian applications. In particular, we consider sampling of the prior predictive distribution for approximate Bayesian computation (ABC), and the computation of Bayesian $p$-values for testing prior weak informativeness. Through minor code alterations, we show that SIMD operations can improve the floating point arithmetic performance resulting in up to $6\times$ improvement in the overall serial algorithm performance. Furthermore $4$-way parallel versions can lead to almost $19\times$ improvement over a na\"{i}ve serial implementation. We illustrate the potential of SIMD operations for accelerating Bayesian computations and provide the reader with essential implementation techniques required to exploit modern massively parallel processing environments using standard software development tools.

Single index model is a powerful yet simple model, widely used in statistics, machine learning, and other scientific fields. It models the regression function as $g()$, where a is an unknown index vector and x are the features. This paper deals with a nonlinear generalization of this framework to allow for a regressor that uses multiple index vectors, adapting to local changes in the responses. To do so we exploit the conditional distribution over function-driven partitions, and use linear regression to locally estimate index vectors. We then regress by applying a kNN type estimator that uses a localized proxy of the geodesic metric. We present theoretical guarantees for estimation of local index vectors and out-of-sample prediction, and demonstrate the performance of our method with experiments on synthetic and real-world data sets, comparing it with state-of-the-art methods.

In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex optimization, the sample complexity of our algorithms depends only on the margin of the data, and not on the dimension.

Most of the machine learning algorithms are parametric. What do we mean by parametric? Let's say if we are trying to model an linear regression model with one dependent variable and one independent variable. The best fit we are looking is the line equations with optimized parameters. The parameters could be the intercept and coefficient. For any classification algorithm, we will try to get a boundary.

"Graphs have become very powerful, they're fundamental, and they're only becoming more and more important," said Dr. Steven Skiena, Director of the AI Institute at Stony Brook University. Graphs are a fundamental part of computer science, and they are only getting larger. Analyzing graphs using machine learning is powerful but requires translating them into numerical values. That's where graph algorithms come in. In this week's five-minute interview (conducted at GraphConnect 2018 in NYC), we spoke with Dr. Steven Skiena, author of The Algorithm Design Manual and The Data Science Design Manual, about his work on DeepWalk, slated to be incorporated into the Neo4j graph algorithm library.

In the syntax below, we are asking Python to import numpy and pandas package. The'as' is used to alias package name.

Word embeddings are increasingly attracting the attention of researchers dealing with semantic similarity and analogy tasks. However, finding the optimal hyper-parameters remains an important challenge due to the resulting impact on the revealed analogies mainly for domain-specific corpora. While analogies are highly used for hypotheses synthesis, it is crucial to optimise word embedding hyper-parameters for precise hypothesis synthesis. Therefore, we propose, in this paper, a methodological approach for tuning word embedding hyper-parameters by using the stability of k-nearest neighbors of word vectors within scientific corpora and more specifically Computer Science corpora with Machine learning adopted as a case study. This approach is tested on a dataset created from NIPS (Conference on Neural Information Processing Systems) publications, and evaluated with a curated ACM hierarchy and Wikipedia Machine Learning outline as the gold standard. Our quantitative and qualitative analysis indicate that our approach not only reliably captures interesting patterns like "unsupervised_learning is to kmeans as supervised_learning is to knn", but also captures the analogical hierarchy structure of Machine Learning and consistently outperforms the \(61\%\) sate-of-the-art embeddings on syntactic accuracy with \(68\%\).