Bashir Sadeghi

PhD Student
CV
GitHub
Google Scholar
Website
Email
sadeghibobfuscate@msu.edu

I am a fourth-year Ph.D. student in the Computer Science Department at Michigan State University under the supervision of Dr. Vishnu Boddeti. I obtained my master’s degree in Electrical and Electronic Engineering.

Research Interests

Machine Learning, Signal Processing, Deep Learning, Computer Vision, Signal Processing on Graph

Current Projects

  • Fair and Privacy-Preserving Representation Learning
  • Learning via Functions in Reproducing Kernel Hilbert Spaces
  • Generalized Sampling-Reconstruction Processes and Applications to Sampling on Graph
  • Measures of Independence

Computer Skills

  • C/C++, Python, Matlab
  • Deep Learning: Pytorch, TensorFlow
Papers

Utility-Fairness Trade-Offs and How to Find Them

On Characterizing the Trade-off in Invariant Representation Learning

Adversarial Representation Learning With Closed-Form Solvers

Imparting Fairness to Pre-Trained Biased Representations

Adversarial Representation Learning With Closed-Form Solvers

On the Global Optima of Kernelized Adversarial Representation Learning

Constrained Sampling: Optimum Reconstruction in Subspace with Minimax Regret Constraint