Stochastic approximation deals with the problem of finding zeros of a function expressed as an expectation of a random variable. In this thesis we propose convergent algorithms for problems in optimization, statistical ...

Image filtering is a fundamental preprocessing task in computer vision and image processing. Various linear and nonlinear filters are routinely used for enhancement, upsampling, sharpening, reconstruction, etc. The focus ...

Graph neural networks gained significant attention for graph representation and classification in the machine learning community. For graph classification, different pooling techniques are introduced, but none of them has ...

Reduced feedback schemes are a crucial component of orthogonal frequency division multiplexing-based 4G and 5G cellular systems that use downlink scheduling, adaptive modulation and coding, and multiple-input-multiple-output ...

Recent decades have seen a revolution in the way people communicate, buy products, learn new things, and share life experiences. This has spurred the growth of online platforms that enable users from all over the globe to ...

A Separation Kernel is a small specialized microkernel that provides a sand-boxed execution environment for a given set of processes (also called \subjects"). The subjects may communicate only via declared memory channels, ...

Biomolecules like proteins are the basic building blocks of living systems. It has been observed that the structure of a biomolecule plays an important role in defining its function. In this thesis, we describe novel ...

Smoothing (diffusion) is a fundamental task in low-level vision and image processing. In the context of natural images, where edges (sharp discontinuities) play an important psychovisual role, the smoothing process needs ...

Deep neural network-based models have achieved unprecedented performance levels over many tasks in the traditional supervised setting and scale well with large quantities of data. On the other hand, improving performance ...

Graph processing at scales of millions-billions of vertices and edges has become common to solve real-world problems in domains like social networks, smart cities and genomics. Distributed "Big Data" platforms for graph ...