Search
Now showing items 1-10 of 14
Temporal Point Processes for Forecasting Events in Higher-Order Networks
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 ...
Exploring Fairness and Causality in Online Decision-Making
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 ...
Investigating Neural Mechanisms of Word Learning and Speech Perception
Language learning and speech perception are remarkable feats performed by the human brain, involving complex neural mechanisms that allow us to understand and communicate with one another. Unravelling the mysteries of these ...
Sparse Input View Synthesis: 3D Representations and Reliable Priors
Novel view synthesis refers to the problem of synthesizing novel viewpoints of a scene given the images from a few viewpoints. This is a fundamental problem in computer vision and graphics, and enables a vast variety of ...
Tight Frames, Non-convex Regularizers, and Quantized Neural Networks for Solving Linear Inverse Problems
The recovery of a signal/image from compressed measurements involves formulating an optimization problem and solving it using an efficient algorithm. The optimization objective involves data fidelity, which is responsible ...
Boolean Functional Synthesis using Gated Continuous Logic Networks
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 ...
Inverse Problems in 3D Full-wave Electromagnetics
An inverse problem in Electromagnetics (EM) refers to the process of reconstructing the physical system by processing the measured data of its electromagnetic properties. Inverse problems are typically ill-posed, and this ...
Performance Characterization and Optimizations of Traditional ML Applications
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 ...
Novel First-order Algorithms for Non-smooth Optimization Problems in Machine Learning
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 ...
Low Power Machine Learning Systems for Energy Efficient Edge Devices
Energy-efficient devices are essential in the world of edge computing and the tiny Machine
Learning (tinyML) paradigm. Edge devices are often constrained by the available compu-
tational power and hardware resource. To ...