Microsoft Technology Licensing, LLC

Aditya Nori

Kapil Vaswani

Sriram Kottarakurichi Rajamani

Sumit Gulwani

Trishul A Chilimbi

Andrew Donald Gordon

Thore Graepel

Krishna Kumar Mehra

Trishul Amit Madhukar Chilimbi

Benjamin Robert Liblit

Johannes Borgstroem

Rahul Srinivasan

There is provided a method and system for modeling a data generating process. The method includes generating a dyadic Bayesian model including a pair of probabilistic functions representing a prior distribution and a sampling distribution, and modeling a data generating process based on the dyadic Bayesian model using observed data. The method includes generating a learner object for the dyadic Bayesian model. The method further includes training the dyadic Bayesian model with the learner object based on the observed data to produce a trained dyadic Bayesian model. The method also includes generating a posterior distribution over parameters based on the trained dyadic Bayesian model. The method also further includes generating a posterior predictive distribution based on the posterior distribution. The method also includes predicting an outcome of observable variables based on the posterior predictive distribution.

Modeling a data generating process using dyadic Bayesian models

A quantified belief propagation (QBP) algorithm receives as input an existentially quantified boolean formula (QBF) of existentially quantified boolean variables, universally quantified variables, and boolean operators. A tripartite graph is constructed, and includes (i) there-exists nodes that correspond to and represent the existentially quantified variables, (ii) for-all nodes that correspond to and represent the universally quantified variables, and (iii) sub-formula nodes that correspond to and represent sub-formulas of the QBF. A set of boolean values of the existentially quantified variables is found by (i) passing a first message from an arbitrary sub-formula node to an arbitrary for-all node, and (ii) in response, passing a second message from the arbitrary for-all node to the arbitrary sub-formula node.

Program synthesis with existentially and universally quantified belief propagation using probabilistic inference

This paper describes preferential path profiling, which enables profiling a specified subset of all possible program paths with very low overhead. Preferential path profiling compactly identifies paths of interest using an array. More specifically, PPP assigns a unique and compact path index identifier to all interesting paths that can be used to index into a path array. The path array contains a second path value identifier that is used to distinguish interesting paths from other program paths This path numbering allows the implementation of preferential path profiling to use array-based counters instead of hash table-based counters for identifying paths of interest and gathering path profiles, which significantly reduces execution time and computational resource overhead during profiling.

Preferential path profiling

The method executes the application and if there are no errors from the execution of the application, the method ends. If errors exist, the errors are collected from the execution of the application in an error report. Labeled application paths are created by adding a unique label to individual application paths where the application paths are individual loops and individual functions in the application. An analysis is created of the labeled application paths by executing the application with the labeled paths, reviewing the error report for data related to the labels and if an error is sufficiently related to application paths with labels, storing the path that created the errors in a report. If an error is not sufficient related to the application path with labels, the method is repeated by the creating the analysis again by substituting additional application paths for the application paths.

Statistical debugging using paths and adaptive profiling

Growing community of inventors

Bengaluru, India

Aditya Nori