Exogenous state variables and rewards can slow reinforcement learning by injecting uncontrolled variation into the reward signal. This paper formalizes exogenous state variables and rewards and shows that if the reward function decomposes additively into endogenous and exogenous components, the MDP can be decomposed into an exogenous Markov Reward Process (based on the exogenous reward) and an endogenous Markov Decision Process (optimizing the endogenous reward). Any optimal policy for the endogenous MDP is also an optimal policy for the original MDP, but because the endogenous reward typically has reduced variance, the endogenous MDP is easier to solve. We study settings where the decomposition of the state space into exogenous and endogenous state spaces is not given but must be discovered. The paper introduces and proves correctness of algorithms for discovering the exogenous and endogenous subspaces of the state space when they are mixed through linear combination. These algorithms can be applied during reinforcement learning to discover the exogenous space, remove the exogenous reward, and focus reinforcement learning on the endogenous MDP. Experiments on a variety of challenging synthetic MDPs show that these methods, applied online, discover large exogenous state spaces and produce substantial speedups in reinforcement learning.

Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for network systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward function. In this work, we tackle the communication load balancing problem from an inverse reinforcement learning (IRL) approach. To the best of our knowledge, this is the first time IRL has been successfully applied in the field of communication load balancing. Specifically, first, we infer a reward function from a set of demonstrations, and then learn a reinforcement learning load balancing policy with the inferred reward function. Compared to classical RL-based solution, the proposed solution can be more general and more suitable for real-world scenarios. Experimental evaluations implemented on different simulated traffic scenarios have shown our method to be effective and better than other baselines by a considerable margin.

In recommendation systems, a large portion of the ratings are missing due to the selection biases, which is known as Missing Not At Random. The counterfactual inverse propensity scoring (IPS) was used to weight the imputation error of every observed rating. Although effective in multiple scenarios, we argue that the performance of IPS estimation is limited due to the uncertainty miscalibration of propensity estimation. In this paper, we propose the uncertainty calibration for the propensity estimation in recommendation systems with multiple representative uncertainty calibration techniques. Theoretical analysis on the bias and generalization bound shows the superiority of the calibrated IPS estimator over the uncalibrated one. Experimental results on the coat and yahoo datasets shows that the uncertainty calibration is improved and hence brings the better recommendation results.

Deep generative learning cannot only be used for generating new data with statistical characteristics derived from input data but also for anomaly detection, by separating nominal and anomalous instances based on their reconstruction quality. In this paper, we explore the performance of three unsupervised deep generative models -- variational autoencoders (VAEs) with Gaussian, Bernoulli, and Boltzmann priors -- in detecting anomalies in flight-operations data of commercial flights consisting of multivariate time series. We devised two VAE models with discrete latent variables (DVAEs), one with a factorized Bernoulli prior and one with a restricted Boltzmann machine (RBM) as prior, because of the demand for discrete-variable models in machine-learning applications and because the integration of quantum devices based on two-level quantum systems requires such models. The DVAE with RBM prior, using a relatively simple -- and classically or quantum-mechanically enhanceable -- sampling technique for the evolution of the RBM's negative phase, performed better than the Bernoulli DVAE and on par with the Gaussian model, which has a continuous latent space. Our studies demonstrate the competitiveness of a discrete deep generative model with its Gaussian counterpart on anomaly-detection tasks. Moreover, the DVAE model with RBM prior can be easily integrated with quantum sampling by outsourcing its generative process to measurements of quantum states obtained from a quantum annealer or gate-model device.

Conditional Neural Processes~(CNPs) formulate distributions over functions and generate function observations with exact conditional likelihoods. CNPs, however, have limited expressivity for high-dimensional observations, since their predictive distribution is factorized into a product of unconstrained (typically) Gaussian outputs. Previously, this could be handled using latent variables or autoregressive likelihood, but at the expense of intractable training and quadratically increased complexity. Instead, we propose calibrating CNPs with an adversarial training scheme besides regular maximum likelihood estimates. Specifically, we train an energy-based model (EBM) with noise contrastive estimation, which enforces EBM to identify true observations from the generations of CNP. In this way, CNP must generate predictions closer to the ground-truth to fool EBM, instead of merely optimizing with respect to the fixed-form likelihood. From generative function reconstruction to downstream regression and classification tasks, we demonstrate that our method fits mainstream CNP members, showing effectiveness when unconstrained Gaussian likelihood is defined, requiring minimal computation overhead while preserving foundation properties of CNPs.

This study evaluates the robustness of two state-of-the-art deep contextual language representations, ELMo and DistilBERT, on supervised learning of binary protest news classification and sentiment analysis of product reviews. A "cross-context" setting is enabled using test sets that are distinct from the training data. Specifically, in the news classification task, the models are developed on local news from India and tested on the local news from China. In the sentiment analysis task, the models are trained on movie reviews and tested on customer reviews. This comparison is aimed at exploring the limits of the representative power of today's Natural Language Processing systems on the path to the systems that are generalizable to real-life scenarios. The models are fine-tuned and fed into a Feed-Forward Neural Network and a Bidirectional Long Short Term Memory network. Multinomial Naive Bayes and Linear Support Vector Machine are used as traditional baselines. The results show that, in binary text classification, DistilBERT is significantly better than ELMo on generalizing to the cross-context setting. ELMo is observed to be significantly more robust to the cross-context test data than both baselines. On the other hand, the baselines performed comparably well to ELMo when the training and test data are subsets of the same corpus (no cross-context). DistilBERT is also found to be 30% smaller and 83% faster than ELMo. The results suggest that DistilBERT can transfer generic semantic knowledge to other domains better than ELMo. DistilBERT is also favorable in incorporating into real-life systems for it requires a smaller computational training budget. When generalization is not the utmost preference and test domain is similar to the training domain, the traditional ML algorithms can still be considered as more economic alternatives to deep language representations.

Ready to build the future with Deep Neural Networks? Stand on the shoulder of TensorFlow and Keras for Machine Learning.

Machine learning models have made many decision support systems to be faster, more accurate, and more efficient. However, applications of machine learning in network security face a more disproportionate threat of active adversarial attacks compared to other domains. This is because machine learning applications in network security such as malware detection, intrusion detection, and spam filtering are by themselves adversarial in nature. In what could be considered an arm's race between attackers and defenders, adversaries constantly probe machine learning systems with inputs that are explicitly designed to bypass the system and induce a wrong prediction. In this survey, we first provide a taxonomy of machine learning techniques, tasks, and depth. We then introduce a classification of machine learning in network security applications. Next, we examine various adversarial attacks against machine learning in network security and introduce two classification approaches for adversarial attacks in network security. First, we classify adversarial attacks in network security based on a taxonomy of network security applications. Secondly, we categorize adversarial attacks in network security into a problem space vs feature space dimensional classification model. We then analyze the various defenses against adversarial attacks on machine learning-based network security applications. We conclude by introducing an adversarial risk grid map and evaluating several existing adversarial attacks against machine learning in network security using the risk grid map. We also identify where each attack classification resides within the adversarial risk grid map.

The transition model is used to imagine possible outcomes of taking the action/option, which are then evaluated by the value functions to change the policies and the value functions themselves. This process is called planning. Planning, like everything else in the architecture, is expected to be continual and temporally uniform. On every step there will be some amount of planning, perhaps a series of small planning steps, but planning would typically not be complete in a single time step and thus would be slow compared to the speed of agent-environment interaction. Planning is an ongoing process that operates asynchronously, in the background, whenever it can be done without interfering with the first three components, all of which must operate on every time step and are said to run in the foreground.

This article is written for pedagogical purposes aiming at practitioners trying to estimate the finite support of continuous probability distributions, i.e., the minimum and the maximum of a distribution defined on a finite domain. Generalized Pareto distribution GP({\theta}, {\sigma}, {\xi}) is a three-parameter distribution which plays a key role in Peaks-Over-Threshold framework for tail estimation in Extreme Value Theory. Estimators for GP often lack analytical solutions and the best known Bayesian methods for GP involves numerical methods. Moreover, existing literature focuses on estimating the scale {\sigma} and the shape {\xi}, lacking discussion of the estimation of the location {\theta} which is the lower support of (minimum value possible in) a GP. To fill the gap, we analyze four two-parameter subclasses of GP whose conjugate priors can be obtained analytically, although some of the results are known. Namely, we prove the conjugacy for {\xi} > 0 (Pareto), {\xi} = 0 (Shifted Exponential), {\xi} < 0 (Power), and {\xi} = -1 (Two-parameter Uniform).