Vishnu Lokhande
Email:lokhande [at] cs [dot] wisc [dot] edu

Hello there! Let's begin with a quote,
"What I cannot create, I do not understand" - Richard Feynman

I am a PhD student studying computer vision at the University of Wisconsin-Madison . My interests revolve around constrained and stochastic optimization problems and their applications to Computer Vision. I am very fortunate to be advised by Prof. Vikas Singh .

I am also lucky to have been associated with the following wonderful mentors: Julian Yarkony (Verisk), Sathya Ravi (UIC), Vibhav Vineet (MSR), Rudra Chakraborty (Amazon), Kihyuk Sohn (Google)

Prior to my graduate studies, I received my bachelor's degree in Electrical Engineering from IIT Kanpur where I was advised by Prof. Laxmidhar Behera.

CV (updated Oct'21)  /  Github /  Scholar /  Twitter

I'm open to conversations on full-time positions! If you are interested, please feel free to contact me .






News

    [Oct 2021] Participated in 2021 CRCNS Meeting CRCNS Meeting.
    [Jun 2021] Invited to participate in Morgridge Entrepreneurial Bootcamp MEB 2021.
    [May 2021] Proud to be an Outstanding reviewer of CVPR 2021 .
    [May 2021] Our paper on Graph Reparameterization in Bayesian Deep Neural Networks was accepted at UAI 2021.
    [Apr 2021] Our abstract on dataset harmonization algorithms was accepted at AAIC 2021.
    [Apr 2021] Our workshop paper on Diffeomorphism invariant neural networks was accepted at DiffCVML 2021.
    [Feb 2021] Invited to give a talk at my alma mater IIT Kanpur on optimization methods in computer vision QIP IITK.
    [Jan 2021] Internship with Google Research, Sunnyvale at my home (again!) .
    [Dec 2020] Our paper on learning invariant representations was accepted at AAAI 2021.
    [Nov 2020] Honored to be selected as a finalist for Microsoft Research PhD Fellowship 2021.
    [Oct 2020] Proud to be a Top 10% of high-scoring reviewers of NeurIPS 2020.
    [Sep 2020] Invited to give a talk on optimization methods for fairness in vison at Utah Data Science Seminar Series . [slides]
    [Jul 2020] Invited to give a talk on our FairALM project at the Princeton Fairness Reading Group.
    [Jul 2020] Our paper on fairness in computer vision - FairALM was accepted at ECCV 2020. [arXiv]
    [Feb 2020] Internship with Microsoft Research, Redmond at my home.
    [Feb 2020] Our Paper on Hermite Polynomial Activations for semi-supervised learning was accepted at CVPR 2020. [arXiv]
    [Nov 2019] Our paper Column Generation Techniques for Entity Resolution received Oral Acceptance at the AAAI 2020. [arXiv]
    [Oct 2019] Our paper on Active Learning with Importance Sampling was accepted to the NeurIPS 2019 Workshop Machine Learning with Gaurantees. [arXiv]
    [Jun 2019] Our paper on Hermite Polynomial Activations for semi-supervised learning received Best Student Paper Award at MMLS 2019.
    [May 2019] Research Internship at Verisk AI Labs.
    [Feb 2019] Passed PhD Qualifying Exam in Machine Learning with a High Pass (P+) grade.
    [Dec 2018] Our paper on Constrained Deep Learning using Conditional Gradient method received Oral Acceptance at AAAI 2019.
    [Dec 2018] Student Volunteer at NeurIPS 2018.
    [Jul 2018] Attended summer school on Fundametals of Data Analysis.
    [Jun 2018] Our paper on "Constrained Deep Learning using Conditional Gradient method" received Spotlight Presentation at MMLS 2018.
    [Jun 2018] Organized Reading Group on Deep learning Theory and Practice.

Publications

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks
Jurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh

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
[Video] [Poster]
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
[Code] [Poster] [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