ronakrm

I'm finishing up my dissertation and looking for what's next! (Open for jobs!)

I am currently a graduate student at the University of Wisconsin-Madison. I am working with Dr. Vikas Singh on machine learning and computer vision projects, some in collaboration with the Wisconsin Alzheimer's Disease Research Center to develop methods for analyzing preclinical datasets.

I completed my undergraduate degree in Computer Engineering at the University of Michigan-Ann Arbor in 2014, and my master's degree in Computer Science at UW-Madison in 2016.

For a take away, check out my Résumé/CV.

Some recent news and travel:

My paper on Discrete Optimal Transport was accepted (top 25%!) to ICLR 2023.
I participated in a one-month Interpretability Experiment at Redwood Research.
I traveled to and presented my recent work on efficient unlearning at CVPR 2022 in New Orleans, USA.

Contact Me.

---

Research Projects and Publications

Efficient Discrete Multi Marginal Optimal Transport Regularization.
Ronak Mehta, Jeffery Kline, Vishnu Suresh Lokhande, Glenn Fung, Vikas Singh.
(top 25%) International Conference on Learning Representations, ICLR 2023.
[Paper]

Deep Unlearning via Randomized Conditionally Independent Hessians.
Ronak Mehta, Sourav Pal, Vikas Singh, Sathya Ravi.
Computer Vision and Pattern Recognition, CVPR 2022.
[Webpage] [Paper] [Code]

Investigating Functional Brain Network Abnormalities via Differential Covariance Trajectory Analysis and Scan Statistics.
Anita Sinha, Ronak Mehta, Veena Nair, Rasmus Birn, Vikas Singh, Vivek Prabhakaran.
International Symposium on Biomedical Imaging, ISBI 2022.
[Paper]

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks.
Yuri Nazarov, Ronak Mehta, Vishnu Lokhande, Vikas Singh.
Uncertainty in Artificial Intelligence, UAI 2021.
[Paper]

Scaling Recurrent Models via Orthogonal Approximations in Tensor Trains.
Ronak Mehta, Rudrasis Chakraborty, Yunyang Xiong, Vikas Singh.
International Conference on Computer Vision, ICCV 2019.
[Paper]

Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
Yunyang Xiong, Ronak Mehta, Vikas Singh.
International Conference on Computer Vision, ICCV 2019.
[Paper]

DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer.
Haoliang Sun, Ronak Mehta, Hao H. Zhou, Zhichun Huang, Sterling C. Johnson, Vivek Prabhakaran, Vikas Singh.
International Conference on Computer Vision, ICCV 2019.
[Paper]

Sampling-free Uncertainty Estimation in Gated Recurrent Units with Applications to Normative Modeling in Neuroimaging.
Seong Jae Hwang, Ronak R. Mehta, Hyunwoo J. Kim, Sterling C. Johnson, Vikas Singh.
Uncertainty in Artificial Intelligence, UAI 2019.
[Paper]

On Training Deep 3D CNN Models with Dependent Samples in Neuroimaging.
Yunyang Xiong, Hyunwoo J. Kim, Bhargav Tangirala, Ronak Mehta, Sterling C. Johnson, Vikas Singh.
Information Processing in Medical Imaging, IPMI 2019.
[Paper]

Finding Differentially Covarying Needles in a Temporally Evolving Haystack: A Scan Statistics Perspective.
Ronak Mehta, Hyunwoo Kim, Shulei Wang, Sterling Johnson, Ming Yuan, Vikas Singh. Quart. Appl. Math. 77 (2018), 357-398
[Webpage] [Paper] [Video]

Robust Blind Deconvolution via Mirror Descent.
Sathya Ravi, Ronak Mehta, Vikas Singh.
[Paper]