--Building spatiotemporal activity models for people's activities in urban spaces is important for understanding the ever-increasing complexity of urban dynamics. With the emergence of Geo-T agged Social Media (GTSM) records, previous studies demonstrate the potential of GTSM records for spatiotemporal activity modeling. However, they ignore Non-GeoT agged Social Media (NGTSM) records, which generally account for the majority of posts (e.g., more than 95% in Twitter), and could represent a great source of information to alleviate the sparsity of GTSM records. Furthermore, in the current spatiotemporal embedding techniques, less focus has been given to the users, who exhibit spatially motivated behaviors. T o bridge this research gap, this work proposes USTAR, a novel online learning method for User-guided SpatioT emporal Activity Representation, which (1) embeds locations, time, and text along with users into the same embedding space to capture their correlations; (2) uses a novel collaborative filtering approach based on two different empirically studied user behaviors to incorporate both NGTSM and GTSM records in learning; and (3) introduces a novel sampling technique to learn spatiotemporal representations in an online fashion to accommodate recent information into the embedding space, while avoiding overfitting to recent records and frequently appearing units in social media streams. Our results show that USTAR substantially improves the state-of-the-art for region retrieval and keyword retrieval and its potential to be applied to other downstream applications such as local event detection. With urbanization, more than half of the today's world population (exactly 55.7% as of 2019 1) live in urban areas. It is projected that the urbanization trend will gradually increase over the next few decades. As a result, it is not only difficult to tackle urban challenges (e.g., controlling traffic congestion, controlling environmental pollution), it is difficult for people in urban areas to find the most suitable activities and places at the right time. For instance, consider an inhabitant in a highly urbanized city like Melbourne. What is the best time to visit Mount Buller, a snowy mountain near Melbourne, for skiing? Up until the early 2000s 2, it was almost impossible to model these complex urban dynamics due to the lack of reliable data sources.

In this paper, we propose a two-step training procedure for source separation via a deep neural network. In the first step we learn a transform (and it's inverse) to a latent space where masking-based separation performance using oracles is optimal. For the second step, we train a separation module that operates on the previously learned space. In order to do so, we also make use of a scale-invariant signal to distortion ratio (SI-SDR) loss function that works in the latent space, and we prove that it lower-bounds the SI-SDR in the time domain. We run various sound separation experiments that show how this approach can obtain better performance as compared to systems that learn the transform and the separation module jointly. The proposed methodology is general enough to be applicable to a large class of neural network end-to-end separation systems.

This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal reg ret bounds or have high per-iteration computational costs. To fi ll this gap, two efficient projection-free online methods call ed ORGFW and MORGFW are proposed for solving stochastic and adversarial OCO problems, respectively. By employing a recursive gradient estimator, our methods achieve optimal regret bounds (up to a logarithmic factor) while possessing low per-iteration computational costs. Experimen tal results demonstrate the efficiency of the proposed methods compared to state-of-the-arts.

For a standard convolutional neural network, optimizing over the input pixels to maximize the score of some target class will generally produce a grainy-looking version of the original image. However, Santurkar et al. (2019) demonstrated that for adversarially-trained neural networks, this optimization produces images that uncannily resemble the target class. In this paper, we show that these "perceptually-aligned gradients" also occur under randomized smoothing, an alternative means of constructing adversarially-robust classifiers. Our finding supports the hypothesis that perceptually-aligned gradients may be a general property of robust classifiers. We hope that our results will inspire research aimed at explaining this link between perceptually-aligned gradients and adversarial robustness.

In this era of big data, feature selection techniques, which have long been proven to simplify the model, makes the model more comprehensible, speed up the process of learning, have become more and more important. Among many developed methods, forward, backward and stepwise feature selection regression remained widely used due to their simplicity and efficiency. However, they are not sufficient enough when it comes to large datasets. In this paper, we analyze the issues associated with those approaches and introduce a novel algorithm that may boost the speed up to 65.77% compared to stepwise while maintaining good performance compared to stepwise selection in terms of the number of selected features and error rates.

ABSTRACT In this paper, we derive generic bounds on the maximum deviations in prediction errors for sequential prediction vi a an information-theoretic approach. The fundamental bounds a re shown to depend only on the conditional entropy of the data point to be predicted given the previous data points. In the asymptotic case, the bounds are achieved if and only if the prediction error is white and uniformly distributed. Index T erms -- Information-theoretic learning, sequential learning, sequential prediction, bounds on performan ce, sequence prediction 1. INTRODUCTION Nowadays machine learning techniques are becoming more and more prevalent in real-time systems such as real-time si g-nal processing, feedback control, and robotics systems. In such systems, on one hand, decisions on the actions are to be made in a sequential manner (sequential decision making); on the other hand, dynamics of the systems as well as the environment that are determined by physical laws will play an indispensable role and must be taken into consideration (interaction with real world).

Deep Reinforcement Learning Based Power control for Wireless Multicast Systems Ramkumar Raghu 1, Pratheek Upadhyaya 1, Mahadesh Panju 1, V aneet Aggarwal 1,2, and Vinod Sharma 1 1 Indian Institute of Science, Bangalore, INDIA. Abstract -- We consider a multicast scheme recently proposed for a wireless downlink in [1]. It was shown earlier that power control can significantly improve its performance. However for this system, obtaining optimal power control is intractable because of a very large state space. Therefore in this paper we use deep reinforcement learning where we use function approximation of the Q-function via a deep neural network. We show that optimal power control can be learnt for reasonably large systems via this approach. The average power constraint is ensured via a Lagrange multiplier, which is also learnt. Finally, we demonstrate that a slight modification of the learning algorithm allows the optimal control to track the time varying system statistics. I NTRODUCTION Wireless networks are being constantly refined to cater for seamless delivery of huge amount of data to the end users. With increased user generated contents and proliferation of social networking sites, almost 78% of mobile data traffic is expected to be due to mobile videos [2]. Also, the requested traffic for these contents is ridden with redundant requests [3]. Thus, multicasting is a natural way to address these requests. A multicast queue with network coding is studied in [4], [5] with infinite library of files.

Our Panoptic-DeepLab is conceptually simple and delivers state-of-the-art results. In particular, we adopt the dual-ASPP and dual-decoder structures specific to semantic, and instance segmentation, respectively. The semantic segmentation branch is the same as the typical design of any semantic segmentation model ( e.g., DeepLab), while the instance segmentation branch is class-agnostic, involving a simple instance center regression. Our single Panoptic-DeepLab sets the new state-of-art at all three Cityscapes benchmarks, reaching 84.2% mIoU, 39.0% AP, and 65.5% PQ on test set, and advances results on the other challenging Mapillary Vistas. 1. Introduction Our bottom-up Panoptic-DeepLab is conceptually simple and delivers state-of-the-art panoptic segmentation results [7]. We adopt dual-ASPP and dual-decoder modules, specific to semantic segmentation and instance segmentation, respectively. The semantic segmentation branch follows the typical design of any semantic segmentation model (e.g., DeepLab [2]), while the instance segmentation prediction involves a simple instance center regression [1, 5], where the model learns to predict instance centers as well as the offset from each pixel to its corresponding center.

The covariance structure of multivariate functional data can be highly complex, especially if the multivariate dimension is large, making extension of statistical methods for standard multivariate data to the functional data setting quite challenging. For example, Gaussian graphical models have recently been extended to the setting of multivariate functional data by applying multivariate methods to the coefficients of truncated basis expansions. However, a key difficulty compared to multivariate data is that the covariance operator is compact, and thus not invertible. The methodology in this paper addresses the general problem of covariance modeling for multivariate functional data, and functional Gaussian graphical models in particular. As a first step, a new notion of separability for multivariate functional data is proposed, termed partial separability, leading to a novel Karhunen-Lo\`eve-type expansion for such data. Next, the partial separability structure is shown to be particularly useful in order to provide a well-defined Gaussian graphical model that can be identified with a sequence of finite-dimensional graphical models, each of fixed dimension. This motivates a simple and efficient estimation procedure through application of the joint graphical lasso. Empirical performance of the method for graphical model estimation is assessed through simulation and analysis of functional brain connectivity during a motor task.

Auto-Model: Utilizing Research Papers and HPO Techniques to Deal with the CASH problem Chunnan Wang, Hongzhi Wang, Tianyu Mu, Jianzhong Li, Hong Gao Department of Computer Science Harbin Institute of T echnology Harbin, China {WangChunnan, wangzh, mutianyu, lijzh, honggao }@hit.edu.cn Abstract --In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems. Choosing the algorithm and hyperpa-rameter setting correctly can promote the overall performance greatly, but users often fail to do so due to the absence of knowledge. How to help users to effectively and quickly select the suitable algorithm and hyperparameter settings for the given task instance is an important research topic nowadays, which is known as the CASH problem. In this paper, we design the Auto-Model approach, which makes full use of known information in the related research paper and introduces hyperparameter optimization techniques, to solve the CASH problem effectively. Auto-Model tremendously reduces the cost of algorithm implementations and hyperparameter configuration space, and thus capable of dealing with the CASH problem efficiently and easily. T o demonstrate the benefit of Auto-Model, we compare it with classical Auto-Weka approach. The experimental results show that our proposed approach can provide superior results and achieves better performance in a short time. Index T erms--Algorithm selection, Hyperparameter optimization, Combined algorithm selection and hyperparameter optimization problem, Auto-Weka, Classification algorithms I. I NTRODUCTION In many fields, such as machine learning, data mining, artificial intelligence and constraint satisfaction, a variety of algorithms and heuristics have been developed to address the same type of problem [1], [2]. Each of these algorithms has its own advantages and disadvantages, and often they are complementary in the sense that one algorithm works well when others fail and vice versa [2]. If we are capable of selecting the algorithm and hyperparameter setting best suited to the task instance, any particular task instance will be well solved, and our ability of dealing with the problem will be improved considerably [3]. However, it is not trivial to achieve this goal. There are a mass of powerful and different algorithms to deal with a certain problem, and these algorithms have completely different hyperparameters, which have great effect on their performance. Even domain experts cannot easily and correctly select the appropriate algorithm with corresponding optimal hyperparameters from such a huge and complex choice space.