Venkata Gandikota

Candidate Bio:

I am a postdoctoral researcher in the College of Information and Computer Sciences at the University of Massachusetts at Amherst, working with Prof. Arya Mazumdar. Before this, I was a postdoctoral fellow at Johns Hopkins University, working with Prof. Xin Li on error-correcting codes. I received my Ph.D. in Computer Science from Purdue University under the supervision of Prof. Elena Grigorescu. I am interested in the foundations of data science and machine learning. In the past, I have thoroughly enjoyed working on lattices and error-correcting codes.

Research Summary:

"My research explores the theoretical aspects of data science with a focus on data recovery from noise. Noise in data often occurs unavoidably either through the data acquisition process because of device limitations or possibly due to transmission through a noisy channel. Recovering the underlying data points after corruption is a fundamental question and has received much well-deserved attention.

In my research, I have explored the algorithmic aspects of recovering various patterned and structured datasets from noise. In particular, I have looked into the recovery of sparse datasets, and datasets with algebraic and geometric structures from noise. I have also studied certain aspects of distributed machine learning related to the data recovery problem."

Teaching Aims:

"I am fortunate to have experienced a diverse set of teaching styles through the course of my graduate and undergraduate studies. My teachers and mentors have played a crucial role in shaping my research and career goals. Similarly, I aspire to have a meaningful impact on the next generation through my enthusiasm and passion for teaching. My teaching style has been formed through the course of several experiences as a student and researcher. These include assisting various undergraduate mathematics and computer science courses, mentoring and working closely with undergraduate and graduate students, and through countless presentations at seminars and reading groups.
Principles:
1) Developing intuition through visualizations
2) Team-based learning
3) Example based teaching
4) Having structured courses
5) Encouraging diversity and community outreach
Courses:
- Undergraduate: Data Structures & Algorithms.
- Graduate: Algorithms, Complexity Theory, Foundations of Data Science & ML, Optimization.
- Special Topics: Coding Theory, Lattice Algorithms, Mathematical Toolkit. "

Keywords: coding theory, lattices, machine learning, sublinear-time algorithms, compressed sensing

All Job Candidates