Tony Jebara is a Professor of Computer Science at Columbia University and Director of Machine Learning Research at Netflix. His research intersects computer science and statistics to develop new frameworks for learning from data with applications in social networks, spatio-temporal data, vision and text. At the Deep Learning Summit in Boston, on April 2016, Tony presented'Double-Cover Inference in Deep Belief Networks'. I caught up with him to hear more about his work at Netflix and his thoughts on the recent advancements in deep learning. Tell us more about your work as Director of Machine Learning Research at Netflix.

Genpact (NYSE: G), a global leader in digitally-powered business process management and services, announces that it has entered into a definitive agreement to acquire PNMsoft, a Gartner Magic Quadrant-rated dynamic workflow, case management and work optimization solutions provider based around Tel Aviv, Israel. PNMsoft complements and easily integrates pre-existing systems of records that typically host manual process work, and will act as a core component in Genpact's digital portfolio whose roadmap comprises close to 100 digital solution components ("digital assets"). Terms of the transaction were not disclosed. Closing is subject to satisfaction of certain customary conditions and expected in the third quarter. The transaction is not expected to be material to current year financial performance.

Contagions such as the spread of popular news stories, or infectious diseases, propagate in cascades over dynamic networks with unobservable topologies. However, "social signals" such as product purchase time, or blog entry timestamps are measurable, and implicitly depend on the underlying topology, making it possible to track it over time. Interestingly, network topologies often "jump" between discrete states that may account for sudden changes in the observed signals. The present paper advocates a switched dynamic structural equation model to capture the topology-dependent cascade evolution, as well as the discrete states driving the underlying topologies. Conditions under which the proposed switched model is identifiable are established. Leveraging the edge sparsity inherent to social networks, a recursive $\ell_1$-norm regularized least-squares estimator is put forth to jointly track the states and network topologies. An efficient first-order proximal-gradient algorithm is developed to solve the resulting optimization problem. Numerical experiments on both synthetic data and real cascades measured over the span of one year are conducted, and test results corroborate the efficacy of the advocated approach.

One of the most basic functions of language is to refer to objects in a shared scene. Modeling reference with continuous representations is challenging because it requires individuation, i.e., tracking and distinguishing an arbitrary number of referents. We introduce a neural network model that, given a definite description and a set of objects represented by natural images, points to the intended object if the expression has a unique referent, or indicates a failure, if it does not. The model, directly trained on reference acts, is competitive with a pipeline manually engineered to perform the same task, both when referents are purely visual, and when they are characterized by a combination of visual and linguistic properties.

In a conventional signal detection problem, the goal is to design a system for detecting a specific signal of interest [1]. The performance of such systems degrades if the signal evolves over time or for other known signals. Due to the advent of Big Data applications, modern detection systems are expected to perform signal detection tasks for different signal models. Hence, it is desirable to build a universal system which is flexible enough to generalize to several signal models. This paper considers a Wireless Sensor Network (WSN) consisting of a number of sensors and a FC. WSNs often operate with severe resource limitations. Consequently, minimizing the system complexity in terms of communication is critical [2]. For example, resources can be conserved if the nodes do not transmit irrelevant or redundant data. Such transmissions can be avoided through dimensionality reduction [3].

The input data features set for many data driven tasks is high-dimensional while the intrinsic dimension of the data is low. Data analysis methods aim to uncover the underlying low dimensional structure imposed by the low dimensional hidden parameters by utilizing distance metrics that consider the set of attributes as a single monolithic set. However, the transformation of the low dimensional phenomena into the measured high dimensional observations might distort the distance metric, This distortion can effect the desired estimated low dimensional geometric structure. In this paper, we suggest to utilize the redundancy in the attribute domain by partitioning the attributes into multiple subsets we call views. The proposed methods utilize the agreement also called consensus between different views to extract valuable geometric information that unifies multiple views about the intrinsic relationships among several different observations. This unification enhances the information that a single view or a simple concatenations of views provides.

Approximate Bayesian Computation (ABC) is a framework for performing likelihood-free posterior inference for simulation models. Stochastic Variational inference (SVI) is an appealing alternative to the inefficient sampling approaches commonly used in ABC. However, SVI is highly sensitive to the variance of the gradient estimators, and this problem is exacerbated by approximating the likelihood. We draw upon recent advances in variance reduction for SVI [6][13] and likelihood-free inference using deterministic simulations [12] to produce low variance gradient estimators of the variational lower-bound. By then exploiting automatic differentiation libraries [8] we can avoid nearly all model-specific derivations. We demonstrate performance on three problems and compare to existing SVI algorithms. Our results demonstrate the correctness and efficiency of our algorithm.

We develop a flexible framework for low-rank matrix estimation that allows us to transform noise models into regularization schemes via a simple bootstrap algorithm. Effectively, our procedure seeks an autoencoding basis for the observed matrix that is stable with respect to the specified noise model; we call the resulting procedure a stable autoencoder. In the simplest case, with an isotropic noise model, our method is equivalent to a classical singular value shrinkage estimator. For non-isotropic noise models--e.g., Poisson noise-- the method does not reduce to singular value shrinkage, and instead yields new estimators that perform well in experiments. Moreover, by iterating our stable autoencoding scheme, we can automatically generate low-rank estimates without specifying the target rank as a tuning parameter.

Physical and technological processes frequently exhibit intrinsic stochasticity. The main mathematical framework to describe and reason about such systems is provided by the theory of continuous time (Markovian) stochastic processes. Such processes have been well studied in chemical physics for several decades as models of chemical reactions at very low concentrations [Gardiner, 1985, e.g.]. More recently, the theory has found novel and diverse areas of application including systems biology at the single cell level [Wilkinson, 2011], ecology [Volkov et al., 2007] and performance modelling in computer systems [Hillston, 2005], to name but a few. The popularity of the approach has been greatly enhanced by the availability of efficient and accurate simulation algorithms [Gillespie, 1977, Gillespie et al., 2013], which permit a numerical solution of medium-sized systems within a reasonable time frame. As with most of science, many of the application domains of continuous time stochastic processes are becoming increasingly data-rich, creating a critical demand for inference algorithms which can use data to calibrate the models and analyse the uncertainty in the predictions. This raises new challenges and opportunities for statistics and machine learning, and has motivated the development of several algorithms for efficient inference in these systems. In this paper, we focus on the Bayesian approach, and formulate the inverse problem in terms of obtaining an approximation to a posterior distribution over the stochastic process, given observations of the system and using existing scientific information to build a prior model of the process.

Machine Learning has granted incredible power to humans. The power to run tasks in automated manner, the power to make our lives comfrotable, the power to improve things continuously by studying decisions at large sacle . And the power to create species who think better than humans. Read what Google's CEO Mr. Sundar Pichai had to say last week: 'Machine learning is a core, transformative way by which we're rethinking everything we're doing,' Pichai said. 'We're thoughtfully applying it across all our products, be it search, ads, YouTube, or Play.