The response to protests against police brutality, ignited by the murder of Geoge Floyd, have been nothing short of draconian. While government forces on the ground gleefully beat protesters and passersby with batons and doused them with tear gas, the US Border Patrol has deployed Reaper drones to surveil citizens from the skies and the DEA has been tasked with tracking protesters. The outsized surveillance response displayed so far by the Feds has driven concerns from privacy advocates over the potential use of more insidious forms of snooping, from facial recognition algorithms to cell-site simulation (aka the Stingray and Crossbow systems.) People stuck in traffic are witnessing NYPD beat up folks on their way home. "All the technology we have been warning about for a while are starting to come to fruition in these protests," Dave Maass, a senior investigative researcher at digital rights group the Electronic Frontier Foundation, told Reuters on Monday.

We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. Although many algorithms have been proposed for contextual bandit, most of them rely on finding the maximum likelihood estimator at each iteration, which requires $O(t)$ time at the $t$-th iteration and are memory inefficient. A natural way to resolve this problem is to apply online stochastic gradient descent (SGD) so that the per-step time and memory complexity can be reduced to constant with respect to $t$, but a contextual bandit policy based on online SGD updates that balances exploration and exploitation has remained elusive. In this work, we show that online SGD can be applied to the generalized linear bandit problem. The proposed SGD-TS algorithm, which uses a single-step SGD update to exploit past information and uses Thompson Sampling for exploration, achieves $\tilde{O}(\sqrt{dT})$ regret with the total time complexity that scales linearly in $T$ and $d$, where $T$ is the total number of rounds and $d$ is the number of features. Experimental results show that SGD-TS consistently outperforms existing algorithms on both synthetic and real datasets.

Policy evaluation algorithms are essential to reinforcement learning due to their ability to predict the performance of a policy. However, there are two long-standing issues lying in this prediction problem that need to be tackled: off-policy stability and on-policy efficiency. The conventional temporal difference (TD) algorithm is known to perform very well in the on-policy setting, yet is not off-policy stable. On the other hand, the gradient TD and emphatic TD algorithms are off-policy stable, but are not on-policy efficient. This paper introduces novel algorithms that are both off-policy stable and on-policy efficient by using the oblique projection method. The empirical experimental results on various domains validate the effectiveness of the proposed approach.

Early prediction of students at risk (STAR) is an effective and significant means to provide timely intervention for dropout and suicide. Existing works mostly rely on either online or offline learning behaviors which are not comprehensive enough to capture the whole learning processes and lead to unsatisfying prediction performance. We propose a novel algorithm (EPARS) that could early predict STAR in a semester by modeling online and offline learning behaviors. The online behaviors come from the log of activities when students use the online learning management system. The offline behaviors derive from the check-in records of the library. Our main observations are two folds. Significantly different from good students, STAR barely have regular and clear study routines. We devised a multi-scale bag-of-regularity method to extract the regularity of learning behaviors that is robust to sparse data. Second, friends of STAR are more likely to be at risk. We constructed a co-occurrence network to approximate the underlying social network and encode the social homophily as features through network embedding. To validate the proposed algorithm, extensive experiments have been conducted among an Asian university with 15,503 undergraduate students. The results indicate EPARS outperforms baselines by 14.62% ~ 38.22% in predicting STAR.

For rapid growth in technology and automation, human tasks are being taken over by robots as robots have proven to be better with both speed and precision. One of the major and widespread usages of these robots is in the industrial businesses, where they are employed to carry massive loads in and around work areas. As these working environments might not be completely localized and could be dynamically changing, new approaches must be evaluated to guarantee a crash-free way of performing duties. This paper presents a new and efficient fusion algorithm for solving the path planning problem in a custom 2D environment. This fusion algorithm integrates an improved and optimized version of both, A* algorithm and the Artificial potential field method. Firstly, an initial or preliminary path is planned in the environmental model by adopting the A* algorithm. The heuristic function of this A* algorithm is optimized and improved according to the environmental model. This is followed by selecting and saving the key nodes in the initial path. Lastly, on the basis of these saved key nodes, path smoothing is done by artificial potential field method. Our simulation results carried out using Python viz. libraries indicate that the new fusion algorithm is feasible and superior in smoothness performance and can satisfy as a time-efficient and cheaper alternative to conventional A* strategies of path planning.

Exploration in novel settings can be challenging without prior experience in similar domains. However, humans are able to build on prior experience quickly and efficiently. Children exhibit this behavior when playing with toys. For example, given a toy with a yellow and blue door, a child will explore with no clear objective, but once they have discovered how to open the yellow door, they will most likely be able to open the blue door much faster. Adults also exhibit this behavior when entering new spaces such as kitchens. We develop a method, Contextual Prior Prediction, which provides a means of transferring knowledge between interactions in similar domains through vision. We develop agents that exhibit exploratory behavior with increasing efficiency, by learning visual features that are shared across environments, and how they correlate to actions. Our problem is formulated as a Contextual Multi-Armed Bandit where the contexts are images, and the robot has access to a parameterized action space. Given a novel object, the objective is to maximize reward with few interactions. A domain which strongly exhibits correlations between visual features and motion is kinemetically constrained mechanisms. We evaluate our method on simulated prismatic and revolute joints.

The human brain works in an unsupervised way, and more than one brain region is essential for lighting up intelligence. Inspired by this, we propose a brain-like heterogeneous network (BHN), which can cooperatively learn a lot of distributed representations and one global attention representation. By optimizing distributed, self-supervised, and gradient-isolated objective functions in a minimax fashion, our model improves its representations, which are generated from patches of pictures or frames of videos in experiments.

Feature selection is an important and active research area in statistics and machine learning. The Elastic Net is often used to perform selection when the features present non-negligible collinearity or practitioners wish to incorporate additional known structure. In this article, we propose a new Semi-smooth Newton Augmented Lagrangian Method to efficiently solve the Elastic Net in ultra-high dimensional settings. Our new algorithm exploits both the sparsity induced by the Elastic Net penalty and the sparsity due to the second order information of the augmented Lagrangian. This greatly reduces the computational cost of the problem. Using simulations on both synthetic and real datasets, we demonstrate that our approach outperforms its best competitors by at least an order of magnitude in terms of CPU time. We also apply our approach to a Genome Wide Association Study on childhood obesity.

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled by modern ubiquitous computing devices. While several techniques based on hand-crafted feature engineering have been proposed, the current state-of-the-art is represented by deep learning architectures that automatically obtain high level representations and that use recurrent neural networks (RNNs) to extract temporal dependencies in the input. RNNs have several limitations, in particular in dealing with long-term dependencies. We propose a novel deep learning framework, \algname, based on a purely attention-based mechanism, that overcomes the limitations of the state-of-the-art. We show that our proposed attention-based architecture is considerably more powerful than previous approaches, with an average increment, of more than $7\%$ on the F1 score over the previous best performing model. Furthermore, we consider the problem of personalizing HAR deep learning models, which is of great importance in several applications. We propose a simple and effective transfer-learning based strategy to adapt a model to a specific user, providing an average increment of $6\%$ on the F1 score on the predictions for that user. Our extensive experimental evaluation proves the significantly superior capabilities of our proposed framework over the current state-of-the-art and the effectiveness of our user adaptation technique.

We present a method for automatically identifying the causal structure of a dynamical control system. Through a suitable experiment design and subsequent causal analysis, the method reveals, which state and input variables of the system have a causal influence on each other. The experiment design builds on the concept of controllability, which provides a systematic way to compute input trajectories that steer the system to specific regions in its state space. For the causal analysis, we leverage powerful techniques from causal inference and extend them to control systems. Further, we derive conditions that guarantee discovery of the true causal structure of the system and show that the obtained knowledge of the causal structure reduces the complexity of model learning and yields improved generalization capabilities. Experiments on a robot arm demonstrate reliable causal identification from real-world data and extrapolation to regions outside the training domain.