Search
Now showing items 21-30 of 141
Attention-Feedback and Representations in OCR
A Kannada OCR, named Lipi Gnani, has been designed and developed from scratch, with the motivation
of it being able to convert printed text or poetry in Kannada script, without any restriction on vocabulary.
The training ...
Robust Algorithms for recovering planted structures in Semi-random instances
In this thesis, we study algorithms for three fundamental graph problems. These are NP-hard problems which have not been understood completely as there is a signifiicant gap between the algorithmic and the hardness fronts ...
Stochastic Approximation with Markov Noise: Analysis and applications in reinforcement learning
Stochastic approximation algorithms are sequential non-parametric methods for finding a zero
or minimum of a function in the situation where only the noisy observations of the function
values are available. Two time-scale ...
Learning to Adapt Policies for uSD card
Machine Learning(ML) for Systems is a new and promising research area where performance
of computer systems is optimized using machine learning methods. ML for Systems has outperformed
traditional heuristics methods in ...
Achieving Fairness in the Stochastic Multi-Armed Bandit Problem
The classical Stochastic Multi-armed Bandit (MAB) problem provides an abstraction for many
real-world decision making problems such as sponsored-search auctions, crowd-sourcing, wireless
communication, etc. In this work, ...
Experiences in using Reinforcement Learning for Directed Fuzzing
Directed testing is a technique to analyze user-specified target locations in the program. It reduces
the time and effort of developers by excluding irrelevant parts of the program from testing and
focusing on reaching ...
Stochastic approximation with set-valued maps and Markov noise: Theoretical foundations and applications
Stochastic approximation algorithms produce estimates of a desired solution using noisy real world data.
Introduced by Robbins and Monro, in 1951, stochastic approximation techniques have been instrumental in
the asymptotic ...
Structured Regularization Through Convex Relaxations Of Discrete Penalties
Motivation. Empirical risk minimization(ERM) is a popular framework for learning predictive
models from data, which has been used in various domains such as computer vision, text
processing, bioinformatics, neuro-biology, ...
Adaptively Secure Primitives in the Random Oracle Model
Adaptive security embodies one of the strongest notions of security that allows an adversary to corrupt
parties at any point during protocol execution and gain access to its internal state. Since it models reallife
situations ...
Statistical Network Analysis: Community Structure, Fairness Constraints, and Emergent Behavior
Networks or graphs provide mathematical tools for describing and analyzing relational data. They are used in biology to model interactions between proteins, in economics to identify trade alliances among countries, in ...