Akshay Krishnamurthy

Computer Science Department
School of Computer Science
Email: <my first name>kr at cs dot cmu dot edu
Office: 7507 GHC

About me:

I'm a fifth year PhD student in the Computer Science Department at Carnegie Mellon University. In May 2010, I received my undergraduate degree in EECS at UC Berkeley.

I just defended my thesis. I am joining Microsoft Research NYC as a postdoctoral researcher and then the Department of Computer Science at the University of Massachussetts, Amherst as an assistant professor (starting Fall 2016).

I am co-organizing the Advances on Active Learning Workshop at ICML 2015. Submissions are closed but please consider attending.


Research:

My research interests are in machine learning, from both statistical and algorithmic perspectives. I work on discovering and exploiting low dimensional structure, in the form of subspaces, clusters, or graphs in learning problems. I am specifically interested in how interactive learning and adaptive sampling mechanisms can be applied to these structure discovery problems. I have also worked on problems in nonparametric statistics, compressive sensing, and contextual bandit learning. My advisor is Aarti Singh.

Thesis: Interactive Algorithms for Unsupervised Machine Learning. [Proposal].

Preprints:

Minimaxity in Structured Normal Means Inference. Akshay Krishnamurthy. [Arxiv version.]
Extreme Compressive Sampling for Covariance Estimation. Martin Azizyan, Akshay Krishnamurthy, Aarti Singh. [Arxiv version.]
Efficient Contextual Semi-Bandit Learning. Akshay Krishnamurthy, Alekh Agarwal, Miroslav Dudik. [Arxiv version.]
Influence Functions for Machine Learning: Nonparametric Estimators for Entropies, Divergences, and Mutual Informations. Kirthevasan Kandasamy, Akshay Krishnamurthy, Barnabas Poczos, Larry Wasserman, and James M. Robins. [Arxiv version.]
On the Power of Adaptivity in Matrix Completion and Approximation. Akshay Krishnamurthy and Aarti Singh. [Arxiv version.]

Publications:

Learning to search better than your teacher. Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, Hal Daume III, John Langford. To appear in International Conference on Machine Learning, ICML 2015. [Arxiv version.]
On Estimating L_2^2 Divergence. Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos and Larry Wasserman. In Artificial Intelligence and Statistics, AISTATS 2015. [Arxiv version.]
Subspace Learning from Extremely Compressed Measurements. Akshay Krishnamurthy, Martin Azizyan, and Aarti Singh. To appear in Asilomar Conference on Signals, Systems and Computers, 2014. [Arxiv version.]
Nonparametric Estimation of Renyi Divergence and Friends. Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, and Larry Wasserman. In International Conference on Machine Learning, ICML 2014. [ Arxiv version.][code]
Recovering Graph-Structured Activations using Adaptive Compressive Measurements. Akshay Krishnamurthy, James Sharpnack, and Aarti Singh. In Asilomar Conference on Signals, Systems and Computers, 2013. Winner of the Best Student Paper Award. [ Arxiv version.]
Low-Rank Matrix and Tensor Completion Via Adaptive Sampling Akshay Krishnamurthy and Aarti Singh. In Neural Information Processing Systems, NIPS 2013. [Arxiv version.]
Near-Optimal Anomaly Detection in Graphs using Lovasz Extended Scan Statistic. James Sharpnack, Akshay Krishnamurthy, and Aarti Singh. In Neural Information Processing Systems, NIPS 2013. [Arxiv version.]
Detecting Activations over Graphs using Spanning Tree Wavelet Bases. James Sharpnack, Akshay Krishnamurthy and Aarti Singh. In Artificial Intelligence and Statistics, AISTATS 2013 (oral presentation).
Completion of high-rank ultrametric matrices using selective entries. Aarti Singh, Akshay Krishnamurthy, Sivaraman Balakrishnan and Min Xu. In International Conference on Signal Processing and Communications, SPCOM 2012.
Efficient Active Algorithms for Hierarchical Clustering. Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu, and Aarti Singh. In International Conference on Machine Learning, ICML 2012. [code]

Robust Multi-Source Network Tomography using Selective Probes. Akshay Krishnamurthy and Aarti Singh. IEEE International Conference on Computer Communication, INFOCOM 2012.
Noise Thresholds for Spectral Clustering. Sivaraman Balakrishnan, Min Xu, Akshay Krishnamurthy, Aarti Singh. Neural Information Processing Systems, NIPS 2011
DEGAS: De novo discovery of dysregulated pathways in human diseases. Igor Ulitsky, Akshay Krishnamurthy, Richard Karp, Ron Shamir. In PLoS ONE. October 2010.
Fine-Grained Privilege Separation for Web Applications Akshay Krishnamurthy, Adrian Mettler, and David Wagner. WWW 2010. 2010.

Teaching:

Spring 2015: 10-704: Information Processing and Learning (Instructor)
Spring 2013: 10-702: Statistical Machine Learning (Teaching Assistant)
Fall 2012: 15-251: Great Theoretical Ideas on Computer Science (Teaching Assistant)

Notes:

Please excuse (or notify me of) any typos
Some Notes on Nonparametric Goodness-of-Fit Testing