Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Nikhil Rao is active.

Publication


Featured researches published by Nikhil Rao.


knowledge discovery and data mining | 2016

Goal-Directed Inductive Matrix Completion

Si Si; Kai-Yang Chiang; Cho-Jui Hsieh; Nikhil Rao; Inderjit S. Dhillon

Matrix completion (MC) with additional information has found wide applicability in several machine learning applications. Among algorithms for solving such problems, Inductive Matrix Completion(IMC) has drawn a considerable amount of attention, not only for its well established theoretical guarantees but also for its superior performance in various real-world applications. However, IMC based methods usually place very strong constraints on the quality of the features(side information) to ensure accurate recovery, which might not be met in practice. In this paper, we propose Goal-directed Inductive Matrix Completion(GIMC) to learn a nonlinear mapping of the features so that they satisfy the required properties. A key distinction between GIMC and IMC is that the feature mapping is learnt in a supervised manner, deviating from the traditional approach of unsupervised feature learning followed by model training. We establish the superiority of our method on several popular machine learning applications including multi-label learning, multi-class classification, and semi-supervised clustering.


asilomar conference on signals, systems and computers | 2014

Forward — Backward greedy algorithms for signal demixing

Nikhil Rao; Parikshit Shah; Stephen J. Wright

Signal demixing arises in many applications. Common among these are the separation of sparse and low rank components in image and video processing, sparse and group sparse models in multitask learning and spikes and sinusoids in source separation problems. For specific problems of interest, many methods exist to perform recovery, but an approach that generalizes to arbitrary notions of simplicity has not been forthcoming. We propose a framework for signal demixing when the components are defined to be simple in a fairly arbitrary manner. Our method remains computationally simple and can be used in a variety of practical applications.


ieee international workshop on computational advances in multi sensor adaptive processing | 2015

PU matrix completion with graph information

Nagarajan Natarajan; Nikhil Rao; Inderjit S. Dhillon

Motivated by applications in recommendation systems and bioinformatics, we consider the problem of completing a low rank, partially observed binary matrix with graph information. We show that the corresponding problem can be set up in a positive and unlabeled data learning (referred to as PU learning in literature) framework. We make connections to convex optimization and show that existing greedy methods can be used to solve the problem. Experiments on simulated data as well as gene-disease associations data from bioinformatics show that using graphs, and adapting matrix completion in the PU learning setting, yield advantages over the standard binary matrix completion.


international conference on artificial intelligence and statistics | 2012

Universal Measurement Bounds for Structured Sparse Signal Recovery

Nikhil Rao; Benjamin Recht; Robert D. Nowak


neural information processing systems | 2015

Collaborative filtering with graph information: consistency and scalable methods

Nikhil Rao; Hsiang-Fu Yu; Pradeep Ravikumar; Inderjit S. Dhillon


neural information processing systems | 2016

Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction

Hsiang-Fu Yu; Nikhil Rao; Inderjit S. Dhillon


arXiv: Machine Learning | 2011

Tight Measurement Bounds for Exact Recovery of Structured Sparse Signals.

Nikhil Rao; Benjamin Recht; Robert D. Nowak


neural information processing systems | 2016

Structured Sparse Regression via Greedy Hard Thresholding

Prateek Jain; Nikhil Rao; Inderjit S. Dhillon


arXiv: Machine Learning | 2012

Signal Recovery in Unions of Subspaces with Applications to Compressive Imaging

Nikhil Rao; Robert D. Nowak


arXiv: Machine Learning | 2015

Optimal Low-Rank Tensor Recovery from Separable Measurements: Four Contractions Suffice

Parikshit Shah; Nikhil Rao; Gongguo Tang

Collaboration


Dive into the Nikhil Rao's collaboration.

Top Co-Authors

Avatar

Inderjit S. Dhillon

University of Texas at Austin

View shared research outputs
Top Co-Authors

Avatar

Robert D. Nowak

University of Wisconsin-Madison

View shared research outputs
Top Co-Authors

Avatar

Hsiang-Fu Yu

University of Texas at Austin

View shared research outputs
Top Co-Authors

Avatar

Parikshit Shah

University of Wisconsin-Madison

View shared research outputs
Top Co-Authors

Avatar

Benjamin Recht

University of California

View shared research outputs
Top Co-Authors

Avatar

Gongguo Tang

Colorado School of Mines

View shared research outputs
Top Co-Authors

Avatar

Rebecca Willett

University of Wisconsin-Madison

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Cho-Jui Hsieh

University of California

View shared research outputs
Top Co-Authors

Avatar

Kai-Yang Chiang

University of Texas at Austin

View shared research outputs
Researchain Logo
Decentralizing Knowledge