Classification algorithms have been widely used in many application domains. Most of these domains deal with massive collection of data and hence demand classification algorithms that scale well with the size of the data ...

Real-world systems consisting of interacting entities can be effectively represented as time-evolving networks or graphs, where the entities are depicted as nodes, and the interactions between them are represented as ...

Online decision-making under uncertainty is a fundamental aspect of numerous real-world problems across various domains, including online resource allocation, crowd-sourcing, and online advertising. Multi-Armed Bandits ...

Boolean Functional Synthesis (BFS) is a well-known challenging problem in the domain of automated program synthesis from logical specifications. This problem aims to synthesize a Boolean function that is correct-by-construction ...

Even in the era of Deep Learning based methods, traditional machine learning methods with large data sets continue to attract significant attention. However, we find an apparent lack of a detailed performance characterization ...

This thesis is devoted to designing efficient optimization algorithms for machine learning (ML) problems where the underlying objective function to be optimized is convex but not necessarily differentiable. Such non-smooth ...

Networks are ubiquitous. We start our technical work in this thesis by exploring the classical concept of node centrality (also known as influence measure) in information networks. Like clustering, node centrality is also ...

Abstract In recent years, deep neural networks have achieved extraordinary performance on supervised learning tasks. Convolutional neural networks (CNN) have vastly improved the state of the art for most computer vision ...

Machine learning models are increasingly being offered as a service by big companies such as Google, Microsoft and Amazon. They use Machine Learning as a Service (MLaaS) to expose these machine learning models to the ...

We consider the broad framework of supervised learning, where one gets examples of objects together with some labels (such as tissue samples labeled as cancerous or non-cancerous, or images of handwritten digits labeled ...