On Finding the Natural Number of Topics with Latent Dirichlet Allocation: Some Observations

It is important to identify the ``correct'' number of topics in mechanisms like Latent Dirichlet Allocation(LDA) as they determine the quality of features that are presented as features for classifiers like SVM. In this work we propose a measure to identify the correct number of topics and offer empirical evidence in its favor in terms of classification accuracy and the number of topics that are naturally present in the corpus. We show the merit of the measure by applying it on real-world as well as synthetic data sets(both text and images). In proposing this measure, we view LDA as a matrix factorization mechanism, wherein a given corpus C is split into two matrix factors M-1 and M-2 as given by C-d*w = M1(d*t) x Q(t*w).Where d is the number of documents present in the corpus anti w is the size of the vocabulary. The quality of the split depends on ``t'', the right number of topics chosen. The measure is computed in terms of symmetric KL-Divergence of salient distributions that are derived from these matrix factors. We observe that the divergence values are higher for non-optimal number of topics - this is shown by a `dip' at the right value for `t'.

Trace Driven Dynamic Deadlock Detection and Reproduction

Dynamic analysis techniques have been proposed to detect potential deadlocks. Analyzing and comprehending each potential deadlock to determine whether the deadlock is feasible in a real execution requires significant programmer effort. Moreover, empirical evidence shows that existing analyses are quite imprecise. This imprecision of the analyses further void the manual effort invested in reasoning about non-existent defects. In this paper, we address the problems of imprecision of existing analyses and the subsequent manual effort necessary to reason about deadlocks. We propose a novel approach for deadlock detection by designing a dynamic analysis that intelligently leverages execution traces. To reduce the manual effort, we replay the program by making the execution follow a schedule derived based on the observed trace. For a real deadlock, its feasibility is automatically verified if the replay causes the execution to deadlock. We have implemented our approach as part of WOLF and have analyzed many large (upto 160KLoC) Java programs. Our experimental results show that we are able to identify 74% of the reported defects as true (or false) positives automatically leaving very few defects for manual analysis. The overhead of our approach is negligible making it a compelling tool for practical adoption.

Mycobacterium tuberculosis has diminished capacity to counteract redox stress induced by elevated levels of endogenous superoxide

Mycobacterium tuberculosis (Mtb) has evolved protective and detoxification mechanisms to maintain cytoplasmic redox balance in response to exogenous oxidative stress encountered inside host phagocytes. In contrast, little is known about the dynamic response of this pathogen to endogenous oxidative stress generated within Mtb. Using a noninvasive and specific biosensor of cytoplasmic redox state of Mtb, we for first time discovered a surprisingly high sensitivity of this pathogen to perturbation in redox homeostasis induced by elevated endogenous reactive oxygen species (ROS). We synthesized a series of hydroquinone-based small molecule ROS generators and found that ATD-3169 permeated mycobacteria to reliably enhance endogenous ROS including superoxide radicals. When Mtb strains including multidrug-resistant (MDR) and extensively drug-resistant (XDR) patient isolates were exposed to this compound, a dose-dependent, long-lasting, and irreversible oxidative shift in intramycobacterial redox potential was detected. Dynamic redox potential measurements revealed that Mtb had diminished capacity to restore cytoplasmic redox balance in comparison with Mycobacterium smegmatis (Msm), a fast growing nonpathogenic mycobacterial species. Accordingly, Mtb strains were extremely susceptible to inhibition by ATD-3169 but not Msm, suggesting a functional linkage between dynamic redox changes and survival. Microarray analysis showed major realignment of pathways involved in redox homeostasis, central metabolism, DNA repair, and cell wall lipid biosynthesis in response to ATD-3169, all consistent with enhanced endogenous ROS contributing to lethality induced by this compound. This work provides empirical evidence that the cytoplasmic redox poise of Mtb is uniquely sensitive to manipulation in steady-state endogenous ROS levels, thus revealing the importance of targeting intramycobacterial redox metabolism for controlling TB infection. (C) 2015 The Authors. Published by Elsevier Inc.

A Stochastic Approximation Algorithm for Quantile Estimation

In this paper, we present two new stochastic approximation algorithms for the problem of quantile estimation. The algorithms uses the characterization of the quantile provided in terms of an optimization problem in 1]. The algorithms take the shape of a stochastic gradient descent which minimizes the optimization problem. Asymptotic convergence of the algorithms to the true quantile is proven using the ODE method. The theoretical results are also supplemented through empirical evidence. The algorithms are shown to provide significant improvement in terms of memory requirement and accuracy.