Professor James J. (Jong Hyuk) Park received his Ph.D. degree in Graduate School of Information Security from Korea University, Korea. From December, 2002 to July, 2007, Dr. Park had been a research scientist of R&D Institute, Hanwha S&C Co., Ltd., Korea. From September, 2007 to August, 2009, He had been a professor at the Department of Computer Science and Engineering, Kyungnam University, Korea. He is now a professor at the Department of Computer Science and Engineering, Seoul National University of Science and Technology (SeoulTech), Korea. Dr. Park has published about 100 research papers in international journals and conferences.

Canada is a country with a relatively small population of just about 36 million people, but its citizens have still been busy inventing, innovating and entertaining. In the run up to Canada Day, we asked BBC readers to tell us what they thought were some of the biggest contributions the country has made to the world. Here are some of those suggestions. The list of Canadian singers, actors, comedians and entertainers is extensive. Readers flagged artists Shania Twain, Celine Dion, Drake, Leonard Cohen, Joni Mitchell, Neil Young, Arcade Fire, Alanis Morissette and Justin Bieber as just a handful of the musicians who have achieved global fame and swept awards shows for their work.

Genetically modified babies may sound like something out of a science fiction movie, but recent innovations in both gene editing and artificial fertilization technology mean that this idea could become a reality. Scientists focus on gene editing to eliminate certain debilitating hereditary diseases, but the technology could accomplish a lot more. Recently, the team at Superdrug surveyed the public on what they would modify in their future children if they could, and the results are surprising. According to the survey, carried out by Superdrug Online Doctor, prospective parents who viewed baby modification as ethical explained that they would most likely alter their child to make them healthier and more intelligent, followed by increased creativity and attractiveness. When it came to specific physical characteristics, Europeans answered that they would genetically modify their child to be a blonde-haired blued-eyed girl of average height. Americans, on the other hand, identified their ideal child as a black-haired blued-eyed male of above average height.

Accurate real time crime prediction is a fundamental issue for public safety, but remains a challenging problem for the scientific community. Crime occurrences depend on many complex factors. Compared to many predictable events, crime is sparse. At different spatio-temporal scales, crime distributions display dramatically different patterns. These distributions are of very low regularity in both space and time. In this work, we adapt the state-of-the-art deep learning spatio-temporal predictor, ST-ResNet [Zhang et al, AAAI, 2017], to collectively predict crime distribution over the Los Angeles area. Our models are two staged. First, we preprocess the raw crime data. This includes regularization in both space and time to enhance predictable signals. Second, we adapt hierarchical structures of residual convolutional units to train multi-factor crime prediction models. Experiments over a half year period in Los Angeles reveal highly accurate predictive power of our models.

We address the M-best-arm identification problem in multi-armed bandits. A player has a limited budget to explore K arms (M

In this paper we provide a conceptual overview of latent variable models within a probabilistic modeling framework, an overview that emphasizes the compositional nature and the interconnectedness of the seemingly disparate models commonly encountered in statistical practice.

We present a novel Metropolis-Hastings method for large datasets that uses small expected-size minibatches of data. Previous work on reducing the cost of Metropolis-Hastings tests yield variable data consumed per sample, with only constant factor reductions versus using the full dataset for each sample. Here we present a method that can be tuned to provide arbitrarily small batch sizes, by adjusting either proposal step size or temperature. Our test uses the noise-tolerant Barker acceptance test with a novel additive correction variable. The resulting test has similar cost to a normal SGD update. Our experiments demonstrate several order-of-magnitude speedups over previous work.

Many scientific and engineering challenges -- ranging from personalized medicine to customized marketing recommendations -- require an understanding of treatment effect heterogeneity. In this paper, we develop a non-parametric causal forest for estimating heterogeneous treatment effects that extends Breiman's widely used random forest algorithm. In the potential outcomes framework with unconfoundedness, we show that causal forests are pointwise consistent for the true treatment effect, and have an asymptotically Gaussian and centered sampling distribution. We also discuss a practical method for constructing asymptotic confidence intervals for the true treatment effect that are centered at the causal forest estimates. Our theoretical results rely on a generic Gaussian theory for a large family of random forest algorithms. To our knowledge, this is the first set of results that allows any type of random forest, including classification and regression forests, to be used for provably valid statistical inference. In experiments, we find causal forests to be substantially more powerful than classical methods based on nearest-neighbor matching, especially in the presence of irrelevant covariates.

Abstract: In this paper, we face the problem of simulating discrete random variables with general and varying distributions in a scalable framework, where fully parallelizable operations should be preferred. The new paradigm is inspired by the context of discrete choice models. Compared to classical algorithms, we add parallelized randomness, and we leave the final simulation of the random variable to a single associative operation. We characterize the set of algorithms that work in this way, and those algorithms that may have an additive or multiplicative local noise. As a consequence, we could define a natural way to solve some popular simulation problems.

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data, thereby identifying training points most responsible for a given prediction. To scale up influence functions to modern machine learning settings, we develop a simple, efficient implementation that requires only oracle access to gradients and Hessian-vector products. We show that even on non-convex and non-differentiable models where the theory breaks down, approximations to influence functions can still provide valuable information. On linear models and convolutional neural networks, we demonstrate that influence functions are useful for multiple purposes: understanding model behavior, debugging models, detecting dataset errors, and even creating visually-indistinguishable training-set attacks.