Research

Research Interests : Machine Learning, Reinforcement Learning, Statistical Machine Learning, Online Learning, Applied Probability, and Computer Vision

Publications

• Query Complexity of k-NN based Mode Estimation
  Anirudh Singhal, Subham Pirojiwala, Nikhil Karamchandani
  Under review at Information Theory Workshop'20
  
  preprint
  code


• Towards a Unified Framework for Visual Compatibility Prediction
  Anirudh Singhal, Ayush Chopra, Kumar Ayush, Utkarsh Patel, K. Balaji
  Winter Conference on Applications of Computer Vision'20
  
  pdf

Patents

• Deep Learning Based Visual Compatibility Prediction For Bundle Reccomendations (Filed in US Patent Office on May'20)
  

Research Projects

• Bandits with Incomplete Control
  Oct'20-Present
  Working with Prof. Nikhil Karamchandani and Prof. Jayakrishnan Nair on a new Multi-Armed Bandit setting where we don't have freedom to pull every arm.
  


• Adaptive Mode Estimation of Continuous Distribution
  Jan'20-Sep'20
  Working with Prof. Nikhil Karamchandani on using Multi-Armed Bandit Algorithms to estimate mode of a high-dimensional dataset
  
  report


• Reduced Feedback Techniques for Kerdock based MIMO-OFDM Precoders
  Jan'20-Jun'20
  Working with Prof. Kumar Appaiah on reducing the feedback requirements for Kerdock based MIMO-OFDM precoders
  
  report