This paper characterizes the conditional distribution properties of the finite sample ridge regression estimator and uses that result to evaluate total regression and generalization errors that incorporate the inaccuracies committed at the time of parameter estimation. The paper provides explicit formulas for those errors. Unlike other classical references in this setup, our results take place in a fully singular setup that does not assume the existence of a solution for the non-regularized regression problem. In exchange, we invoke a conditional homoscedasticity hypothesis on the regularized regression residuals that is crucial in our developments.

We consider the problem of \textit{best arm identification} with a \textit{fixed budget $T$}, in the $K$-armed stochastic bandit setting, with arms distribution defined on $[0,1]$. We prove that any bandit strategy, for at least one bandit problem characterized by a complexity $H$, will misidentify the best arm with probability lower bounded by $$\exp\Big(-\frac{T}{\log(K)H}\Big),$$ where $H$ is the sum for all sub-optimal arms of the inverse of the squared gaps. Our result disproves formally the general belief - coming from results in the fixed confidence setting - that there must exist an algorithm for this problem whose probability of error is upper bounded by $\exp(-T/H)$. This also proves that some existing strategies based on the Successive Rejection of the arms are optimal - closing therefore the current gap between upper and lower bounds for the fixed budget best arm identification problem.

Our aim is to propose a model of subjective time based on information theory and to investigate its implications relative to two phenomena: 1 Time perception. Why does time appear to slow down when you visit a new place, and speed up once you get familiar with it? Recent findings in psychology, neuroscience, and ethology suggest that perceived duration does not coincide with physical duration, but rather depend on the statistical properties of stimuli. Experiments in psychophysics experiments have shown that, if presented with a train of repeated stimuli at constant time intervals (e.g., a letter, word, object, or face), subjects would perceive them as decreasing in duration [70, 44]. On the other hand, the opposite effect is reported whenever the properties of a train of stimuli are suddenly changed: brighter [10, 66], bigger [41, 73], dynamic [11, 31], or more complex stimuli [54, 49] appear to last longer. Measurements of brain activity have found that longer durations correlate with increased neuronal firing rates, fMRI, or EEG signals [2, 20, 16, 35, 45, 40]. When combined with ideas from information theory, these observations have led to the hypothesis that the subjective duration of a stimulus is proportional to the amount of neural energy required to represent said stimulus, and that this energy is a signature of the coding efficiency [21].

We present a new approach to estimating the interdependence of industries in an economy by applying data science solutions. By exploiting interfirm buyer--seller network data, we show that the problem of estimating the interdependence of industries is similar to the problem of uncovering the latent block structure in network science literature. To estimate the underlying structure with greater accuracy, we propose an extension of the sparse block model that incorporates node textual information and an unbounded number of industries and interactions among them. The latter task is accomplished by extending the well-known Chinese restaurant process to two dimensions. Inference is based on collapsed Gibbs sampling, and the model is evaluated on both synthetic and real-world datasets. We show that the proposed model improves in predictive accuracy and successfully provides a satisfactory solution to the motivated problem. We also discuss issues that affect the future performance of this approach.

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the future observations in the process. We devise a learning algorithm running through episodes, in each episode we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fixed policy. At the end of the episode, an optimization oracle returns the optimal memoryless planning policy which maximizes the expected reward based on the estimated POMDP model. We prove an order-optimal regret bound with respect to the optimal memoryless policy and efficient scaling with respect to the dimensionality of observation and action spaces.

Artificial intelligence, machine intelligence, cognitive computing -- whatever you want to call machines that are capable of understanding and acting upon their environment -- is no longer solely the purview of highly credentialed lab directors and deep-thinking computer scientists. It has entered mainstream consciousness, and the public expects IT to play a leadership role as machine learning enters our workplaces, our living spaces and our lives. Chances are that you are not. Most executives, in the opinion of New York Timestechnology columnist John Markoff, are "ill prepared for this new world in the making." People have been thinking about automated work forever.

A pdf version of this document created using latex can be downloaded by clicking here. Polymorphic malware detection is challenging due to the continual mutations miscreants introduce to successive instances of a particular virus. Such changes are akin to mutations in biological sequences. Recently, high-throughput methods for gene sequence classification have been developed by the bioinformatics and computational biology communities. In this paper, we argue that these methods can be usefully applied to malware detection. Unfortunately, gene classification tools are usually optimized for and restricted to an alphabet of four letters (nucleic acids). Consequently, we have selected the Strand gene sequence classifier, which offers a robust classification strategy that can easily accommodate unstructured data with any alphabet including source code or compiled machine code. To demonstrate Stand's suitability for classifying malware, we execute it on approximately 500GB of malware data provided by the Kaggle Microsoft Malware Classification Challenge (BIG 2015) used for predicting 9 classes of polymorphic malware.

Wisconsin Gov. Scott Walker may be surging as an early favorite for the Republican presidential nomination -- but the numbers show the person leading among potential Iowa caucus-goers often doesn't win. In the Democratic field, Hillary Clinton is the most dominant position ever for a non-incumbent, with odds of clinching the nomination as high as 91 percent. Over at the 538 site launched by statistician Nate Silver, the race is already on to handicap the 2016 presidential contest, a reminder that the season of campaigning, polls, predictions and surveys is descending upon us. Which makes it a perfect time to think about statistics. Even this soon in the game, we'll start to see polling from all sides of the political spectrum, making us ponder which results are valid and which might be biased.

Are you skeptical about machines' ability to effectively aid social science decision making? Machines are becoming ever more intelligent, increasingly able to help humans make decisions across the social science spectrum, but cognitive computing is still in its infancy, with much unexplored ground ahead. Accordingly, government leaders who harness the power of cognitive computing are helping usher in a renaissance of simplified operations and enhanced constituent engagement. The secret to effectively using cognitive computing to aid human decision making lies in teaching computers to ask the right questions while taking account context and staying focused on what computers do well. Computers operate at great speed. But can we teach computers to be good social scientists?

One of Britain's leading computer scientists has criticised the "staggering sexism" in the industry, citing a visit to an artificial intelligence laboratory where a prototype of an "enhanced human" was entirely male. Ursula Martin, a professor of computer science at Oxford University, said that despite attempts to redress the problem, there was still an anti-female bias. She said that universities had attempted to encourage more women to enrol on science and mathematics courses, admitting that the institutions "did not always get it right" but they did try to remove obstacles.