Krishna Pillutla

<last-name> <AT> cs <DOT> washington <DOT> edu

I am a PhD student in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. I am fortunate to be advised by Zaid Harchaoui and Sham Kakade.

My research goals are to design and analyze practical machine learning techniques with provable guarantees, particularly in the large scale setting. I'm currently working on optimization for structured prediction.

Previously, I worked with Nina Balcan for my Master's at Carnegie Mellon University. Before that, I spent 4 wonderful years as an undergrad at IIT Bombay.

Outside of academics, I'm passionate about getting out to the mountains to hike/backpack. I also make some music.

My Research


See DBLP for a full list of publications.

Data Driven Resource Allocation for Distributed Learning

with Travis Dick, Mu Li, Colin White, Nina Balcan, Alex Smola in AISTATS 2017.

On Skewed Multi-Dimensional Distributions: the FusionRP Model, Algorithms and Discoveries

with Zhanpeng Fang, Pravallika Devineni, Danai Koutra, Jie Tang, Christos Faloutsos in
SIAM International Conference on Data Mining (SDM), 2016 .

Master's Thesis: Data Driven Resource Allocation For Distributed Machine Learning

Thesis Committee: Nina Balcan, Alex Smola, Christos Faloutsos
[pdf Slides]


I'm interested in the fusion of Western Music with Indian Classical Music. My wonderful grandmother plays the Veena - we have a blast making some fusion music. For more, check out my YouTube channel.

Some improvization over a composition of mine.

Jazzed up version of a Carnatic Classic, Raghuvamsa Sudha.

A mash up of Coldplay's Fix You with the Indian song Jiyen Kyun.