Search

We introduce PPL Bench, a new benchmark for evaluating Probabilistic Programming Languages (PPLs) on a variety of statistical models. The benchmark includes data generation and evaluation code for a number of models as well as implementations in some common PPLs. All of the benchmark code and PPL implementations are available on Github. We welcome contributions of new models and PPLs and as well as improvements in existing PPL implementations. The purpose of the benchmark is two-fold. First, we want researchers as well as conference reviewers to be able to evaluate improvements in PPLs in a standardized setting. Second, we want end users to be able to pick the PPL that is most suited for their modeling application. In particular, we are interested in evaluating the accuracy and speed of convergence of the inferred posterior. Each PPL only needs to provide posterior samples given a model and observation data. The framework automatically computes and plots growth in predictive log-likelihood on held out data in addition to reporting other common metrics such as effective sample size and $\hat{r}$., Comment: 6 pages, PROBPROG 2020

Online Social Networks (OSNs) provide a platform for users to share their thoughts and opinions with their community of friends or to the general public. In order to keep the platform safe for all users, as well as to keep it compliant with local laws, OSNs typically create a set of community standards organized into policy groups, and use Machine Learning (ML) models to identify and remove content that violates any of the policies. However, out of the billions of content that is uploaded on a daily basis only a small fraction is so unambiguously violating that it can be removed by the automated models. Prevalence estimation is the task of estimating the fraction of violating content in the residual items by sending a small sample of these items to human labelers to get ground truth labels. This task is exceedingly hard because even though we can easily get the ML scores or features for all of the billions of items we can only get ground truth labels on a few thousands of these items due to practical considerations. Indeed the prevalence can be so low that even after a judicious choice of items to be labeled there can be many days in which not even a single item is labeled violating. A pragmatic choice for such low prevalence, $10^{-4}$ to $10^{-5}$, regimes is to report the upper bound, or $97.5\%$ confidence interval, prevalence (UBP) that takes the uncertainties of the sampling and labeling processes into account and gives a smoothed estimate. In this work we present two novel techniques Bucketed-Beta-Binomial and a Bucketed-Gaussian Process for this UBP task and demonstrate on real and simulated data that it has much better coverage than the commonly used bootstrapping technique.

As the coronavirus disease 2019 (COVID-19) continues to be a global pandemic, policy makers have enacted and reversed non-pharmaceutical interventions with various levels of restrictions to limit its spread. Data driven approaches that analyze temporal characteristics of the pandemic and its dependence on regional conditions might supply information to support the implementation of mitigation and suppression strategies. To facilitate research in this direction on the example of the United States, we present a machine-readable dataset that aggregates relevant data from governmental, journalistic, and academic sources on the U.S. county level. In addition to county-level time-series data from the JHU CSSE COVID-19 Dashboard, our dataset contains more than 300 variables that summarize population estimates, demographics, ethnicity, housing, education, employment and income, climate, transit scores, and healthcare system-related metrics. Furthermore, we present aggregated out-of-home activity information for various points of interest for each county, including grocery stores and hospitals, summarizing data from SafeGraph and Google mobility reports. We compile information from IHME, state and county-level government, and newspapers for dates of the enactment and reversal of non-pharmaceutical interventions. By collecting these data, as well as providing tools to read them, we hope to accelerate research that investigates how the disease spreads and why spread may be different across regions. Our dataset and associated code are available at github.com/JieYingWu/COVID-19_US_County-level_Summaries., Comment: Updated 10 September 2020

Single-site Markov Chain Monte Carlo (MCMC) is a variant of MCMC in which a single coordinate in the state space is modified in each step. Structured relational models are a good candidate for this style of inference. In the single-site context, second order methods become feasible because the typical cubic costs associated with these methods is now restricted to the dimension of each coordinate. Our work, which we call Newtonian Monte Carlo (NMC), is a method to improve MCMC convergence by analyzing the first and second order gradients of the target density to determine a suitable proposal density at each point. Existing first order gradient-based methods suffer from the problem of determining an appropriate step size. Too small a step size and it will take a large number of steps to converge, while a very large step size will cause it to overshoot the high density region. NMC is similar to the Newton-Raphson update in optimization where the second order gradient is used to automatically scale the step size in each dimension. However, our objective is to find a parameterized proposal density rather than the maxima. As a further improvement on existing first and second order methods, we show that random variables with constrained supports don't need to be transformed before taking a gradient step. We demonstrate the efficiency of NMC on a number of different domains. For statistical models where the prior is conjugate to the likelihood, our method recovers the posterior quite trivially in one step. However, we also show results on fairly large non-conjugate models, where NMC performs better than adaptive first order methods such as NUTS or other inexact scalable inference methods such as Stochastic Variational Inference or bootstrapping., Comment: StarAI has a 6 page limit excluding references

Algorithm performance in supervised learning is a combination of memorization, generalization, and luck. By estimating how much information an algorithm can memorize from a dataset, we can set a lower bound on the amount of performance due to other factors such as generalization and luck. With this goal in mind, we introduce the Labeling Distribution Matrix (LDM) as a tool for estimating the capacity of learning algorithms. The method attempts to characterize the diversity of possible outputs by an algorithm for different training datasets, using this to measure algorithm flexibility and responsiveness to data. We test the method on several supervised learning algorithms, and find that while the results are not conclusive, the LDM does allow us to gain potentially valuable insight into the prediction behavior of algorithms. We also introduce the Label Recorder as an additional tool for estimating algorithm capacity, with more promising initial results., Comment: Accepted to 12th International Conference on Agents and Artificial Intelligence (ICAART 2020), 7 pages including references

Human Computer Interaction (HCI) is a field in which developer makes a user friendly system. User can interact with a computer system without using any conventional peripheral devices. Marker is used to recognize hand movement accurately & successfully. Researchers establish the mechanism to interact with computer system using computer vision. The interaction is better than normal static keyboard and mouse. This paper represents most of innovative mechanisms of the finger tracking used to interact with a computer system using computer vision., Comment: 4 pages, 8 figures, International Journal of Computer Trends and Technology (IJCTT)

VoIP (Voice over Internet Protocol) is a growing technology during last decade. It provides the audio, video streaming facility on successful implementation in the network. However, it provides the text transport facility over the network. Due to implementation of it the cost effective solution, it can be developed for the intercommunication among the employees of a prestigious organization. The proposed idea has been implemented on the audio streaming area of the VoIP technology. In the audio streaming, the security vulnerabilities are possible on the VoIP server during communication between two parties. In the proposed model, first the VoIP system has been implemented with IVR (Interactive Voice Response) as a case study and with the implementation of the security parameters provided to the asterisk server which works as a VoIP service provider. The asterisk server has been configured with different security parameters like VPN server, Firewall iptable rules, Intrusion Detection and Intrusion Prevention System. Every parameter will be monitored by the system administrator of the VoIP server along with the MySQL database. The system admin will get every update related to the attacks on the server through Mail server attached to the asterisk server. The main beauty of the proposed system is VoIP server alone is configured as a VoIP server, IVR provider, Mail Server with IDS and IPS, VPN server, connection with database server in a single asterisk server inside virtualization environment. The VoIP system is implemented for a Local Area Network inside the university system, Comment: 20 pages, 4 figures, 3 tables, 3 snap shots

Nowadays agile software development is used in greater extend but for small organizations only, whereas MDA is suitable for large organizations but yet not standardized. In this paper the pros and cons of Model Driven Architecture (MDA) and Extreme programming have been discussed. As both of them have some limitations and cannot be used in both large scale and small scale organizations a new architecture has been proposed. In this model it is tried to opt the advantages and important values to overcome the limitations of both the software development procedures. In support to the proposed architecture the implementation of it on Online Polling System has been discussed and all the phases of software development have been explained., Comment: 14 pages,1 Figure,1 Table

Video transmission over mobile ad-hoc networks is becoming important as these networks become more widely used in the wireless networks. We propose a routing-aware multiple description video coding approach to support video transmission over mobile ad-hoc networks with single and multiple path transport. We build a model to estimate the packet loss probability of each packet transmitted over the network based on the standard ad-hoc routing messages and network parameters without losing the RERR message. We then calculate the frame loss probability in order to eliminate error without any loss of data., Comment: 9 pages,2 figures, 1 table for algorithm