Anuran Makur

About Me

I am an Assistant Professor in the Department of Computer Science (CS) and the Elmore Family School of Electrical and Computer Engineering (ECE) at Purdue University, where I am also affiliated with the Center for Innovation in Control, Optimization, and Networks (ICON).

Before joining Purdue, I was a postdoctoral researcher in the Laboratory for Information and Decision Systems (LIDS) and the Institute for Data, Systems, and Society (IDSS) at Massachusetts Institute of Technology (MIT), where I was hosted by Prof. Ali Jadbabaie and Prof. Devavrat Shah. Previously, I completed my Sc.D. from the Department of Electrical Engineering and Computer Science (EECS) at MIT, where I was supervised by Prof. Yury Polyanskiy in LIDS and Prof. Lizhong Zheng in the Research Laboratory of Electronics (RLE).

I am broadly interested in theoretical EECS, statistics, and related applied mathematics problems. In particular, my research interests are in:

  • Theory of Machine Learning
    1. ranking and preference learning
    2. optimization for machine learning
    3. non-parametric and high-dimensional estimation (e.g., matrix estimation, regression, density estimation)

  • Combinatorial Statistics
    1. reconstruction/broadcasting on graphs
    2. interacting particle systems (e.g., opinion dynamics, probabilistic cellular automata)
    3. reliable computation using noisy circuits

  • Information Theory
    1. information/functional inequalities and information contraction
    2. fundamental limits of permutation channels
    3. information theoretic methods for statistical inference (e.g., maximal correlation, modal decompositions)

Prospective Students

Prospective Ph.D. students with:

  1. strong interest in one or more of the topics delineated above,
  2. thorough undergraduate or masters level training in applied mathematics—including, but not limited to, probability and stochastic processes, matrix analysis, real analysis, optimization, discrete mathematics, as well as some exposure to information theory or high-dimensional statistics,
  3. past theoretical research experience,
  4. ability to speak English fluently and write lucidly,
  5. (and perhaps, most importantly) grit,
are encouraged to reach out in the manner outlined below.

If you are a current student at Purdue University interested in working with me for your Ph.D., please send me an email with the subject "Prospective Ph.D. Student" and the following information:

  1. complete academic CV,
  2. one representative publication (where you are an author),
  3. a pointer to one of your mathematical proofs in the above publication that you are particularly proud of,
  4. a brief paragraph indicating a proof in one of my papers that you enjoyed reading along with an explanation of why you enjoyed it.
While I may not respond to every such email, I will read them.

If you are currently applying to Purdue University's CS or ECE Ph.D. programs and are interested in working with me, please indicate this in your application by explicitly mentioning my name as your faculty preference. Do not email me at this time.