Vishnu Lokhande
Email:vishnu.lsvsr[at]gmail[dot]com

Hello there! I am a researcher and engineer specializing in machine learning and computer vision. I hold a PhD in Computer Sciences from the University of Wisconsin-Madison .

My research focus is at the intersection of Machine Learning and Computer Vision, with a specific emphasis on developing practical and interpretable algorithms for high-impact applications such as fairness in algorithmic decision-making, biomedical image analysis, recommender systems, entity resolution, covariate shifts, and data-efficient learning. I draw on techniques from optimization and statistics to provide both theoretical guarantees and real-world performance improvements.

I was very fortunate to be advised by Prof. Vikas Singh . I am also lucky to have been associated with the following wonderful collaborators: Julian Yarkony (Laminaar), Sathya Ravi (UIC), Vibhav Vineet (Microsoft Research), Rudra Chakraborty (Lawrence Livermore), Kihyuk Sohn (Google Brain), Anima Singh (Google Brain), Xinyang Yi (Google Brain).

Before pursuing my graduate studies, I earned a bachelor's degree in Electrical Engineering from IIT Kanpur where I was advised by Prof. Laxmidhar Behera.

Resume  /  LinkedIn  /  Github  /  Scholar  /  Twitter






Publications

Pooling Image Datasets with Multiple Covariate Shift and Imbalance
Sotirios Panagiotis Chytas, Vishnu Suresh Lokhande, Vikas Singh
[OpenReview]
12th International Conference on Learning Representations (ICLR-24)

Efficient Discrete Multi Marginal Optimal Transport Regularization
Ronak Mehta, Jeffery Kline, Vishnu Suresh Lokhande, Glenn Fung, Vikas Singh
[OpenReview] [Code] [Media Coverage]
11th International Conference on Learning Representations (ICLR-23)
(Spotlight Presentation)

Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets
Vishnu Suresh Lokhande, Rudra Chakraborty, Sathya N. Ravi, Vikas Singh
[arXiv] [Code] [Video]
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR-22)

Towards Group Robustness in the presence of Partial Group Labels
Vishnu Suresh Lokhande, Kihyuk Sohn, Jinsung Yoon, Madeleine Udell,
Chen-Yu Lee, Tomas Pfister
[arXiv] [Slides] [Code]
Workshop on Spurious Correlations, Invariance and Stability at ICML 2022

Pooling CSF Measurements Across Multiple Cohorts in the Preclinical Alzheimer's Consortium
Vishnu Suresh Lokhande, Jiangxia Wang, Marilyn S. Albert,
Sterling C. Johnson, Vikas Singh and others.
[Abstract]
2022 Alzheimer's Association International Conference. (AAIC-22)

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks
Jurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh
[Video] [Code]
Thirty-seventh Conference on Uncertainty in Artificial Intelligence (UAI-21)

Constrained Harmonization Algorithm for Pooling Multi-site Datasets
Vishnu Suresh Lokhande, Akshay Mishra, Kersten Diers, Emrah Duzel, Martin Reuter, Barbara Bendlin, Vikas Singh
[Slides] [Poster] [Video]
2021 Alzheimer's Association International Conference. (AAIC-21)

Learning Invariant Representations using Inverse Contrastive Loss
Aditya Kumar Akash, Vishnu Suresh Lokhande, Sathya N. Ravi, Vikas Singh
[Poster] [Code] [Slides]
Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)

FairALM: An Augmented Lagrangian Method for Training Fair Models with Little Regret
Vishnu Suresh Lokhande, Aditya Kumar Akash, Sathya N. Ravi, Vikas Singh
[Video] [Slides] [Code]
16th European Conference on Computer Vision (ECCV-20)

Generating Accurate Pseudo-labels in Semi-Supervised Learning and Avoiding Overconfident Predictions via Hermite Polynomial Activations
Vishnu Suresh Lokhande, Songwong Tasneeyapant, Abhay Venkatesh,
Sathya N. Ravi, Vikas Singh
[Video] [Slides] [Code]
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR-20)
Also, Best Student Paper Award at MMLS 2019

Accelerating Column Generation via Flexible Dual Optimal Inequalities with Application to Entity Resolution
Vishnu Suresh Lokhande, Shaofei Wang, Maneesh Singh, Julian Yarkony
[Code] [Poster] [Slides]
Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20)
(Oral Presentation)

Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
Sathya N. Ravi, Tuan Dinh, Vishnu Suresh Lokhande, Vikas Singh
[Code] [Poster]
Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)
(Oral Presentation)
Also, Spotlight Presentation at MMLS 2018

Useful Links


Webpage credits: this and this