Home

Prateek Jain

  1. Differentially Private Online Learning.

    Mon, 09/19/2011 - 15:01 — SomNambul
    Authors: Prateek Jain, Pravesh Kothari, Abhradeep Thakurta
    Subjects: Learning
    Abstract

    In this paper, we consider the problem of preserving privacy in the online
    learning setting. We study the problem in the online convex programming (OCP)
    framework---a popular online learning setting with several interesting
    theoretical and practical implications---while using differential privacy as
    the formal privacy measure.

  2. Orthogonal Matching Pursuit with Replacement.

    Wed, 06/15/2011 - 15:01 — SomNambul
    Authors: Prateek Jain, Ambuj Tewari, Inderjit S. Dhillon
    Subjects: Information Theory
    Abstract

    In this paper, we consider the problem of compressed sensing where the goal
    is to recover almost all the sparse vectors using a small number of fixed
    linear measurements. For this problem, we propose a novel partial
    hard-thresholding operator that leads to a general family of iterative
    algorithms. While one extreme of the family yields well known hard thresholding
    algorithms like ITI (Iterative Thresholding with Inversion) and HTP (Hard
    Thresholding Pursuit), the other end of the spectrum leads to a novel algorithm
    that we call Orthogonal Matching Pursuit with Replacement (OMPR).

  3. Metric and Kernel Learning using a Linear Transformation.

    Mon, 11/02/2009 - 16:01 — SomNambul
    Authors: Prateek Jain, Inderjit S. Dhillon, Brian Kulis, Jason V. Davis
    Subjects: Learning
    Abstract

    Metric and kernel learning are important in several machine learning
    applications. However, most existing metric learning algorithms are limited to
    learning metrics over low-dimensional data, while existing kernel learning
    algorithms are often limited to the transductive setting and do not generalize
    to new data points. In this paper, we study metric learning as a problem of
    learning a linear transformation of the input data.

  4. Guaranteed Rank Minimization via Singular Value Projection.

    Tue, 10/20/2009 - 12:53 — SomNambul
    Authors: Prateek Jain, Raghu Meka, Inderjit S. Dhillon
    Subjects: Learning
    Abstract

    Minimizing the rank of a matrix subject to affine constraints is a
    fundamental problem with many important applications in machine learning and
    statistics.

  5. XTile: An Error-Correction Package for DNA Self-Assembly.

    Thu, 08/20/2009 - 23:06 — SomNambul
    Authors: Anshul Chaurasia, Sudhanshu Dwivedi, Prateek Jain, Manish K. Gupta
    Subjects: Information Theory
    Abstract

    Self assembly is a process by which supramolecular species form spontaneously
    from their components. This process is ubiquitous throughout the life chemistry
    and is central to biological information processing. It has been predicted that
    in future self assembly will become an important engineering discipline by
    combining the fields of bio molecular computation, nano technology and
    medicine. However error control is a key challenge in realizing the potential
    of self assembly.

Math-arch

Syndicate content