Vishnu Lokhande
Email:lokhande@cs.wisc.edu

Hi! I'm a CS PhD student at the University of Wisconsin-Madison. My interests revolve around Machine Learning and it's application to Computer Vision. I'm being advised by Prof. Vikas Singh .

I graduated with B.Tech. in the Electrical Engineering from IIT Kanpur where I was advised by Prof. Laxmidhar Behera for my senior year thesis.

CV (April'19)  /  LinkedIn  /  Github /  Twitter

News

  • [Jun 2019] Our paper on "Generating Accurate Pseudo-labels via Hermite Polynomials for SSL Confidently" received Student Poster 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 "Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision" 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 and Applications in Computer Vision" received Spotlight Presentation at MMLS 2018.
  • [Jun 2018] Organized Reading Group on Deep learning Theory and Practice.

Publications

Accelerating Column Generation via Flexible Dual Optimal Inequalities with Application to Entity Resolution
Vishnu Suresh Lokhande, Shaofei Wang, Maneesh Singh, Julian Yarkony
Under Review

Generating Accurate Pseudo-labels via Hermite Polynomials for SSL Confidently
Vishnu Suresh Lokhande, Sathya N. Ravi, Songwong Tasneeyapant, Abhay Venkatesh, Vikas Singh
Under Review
Code | Poster | Slides

Also, Student Poster Award at MMLS 2019

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

Also, Spotlight Presentation at MMLS 2018

Useful Links


Webpage credits: this, this and this