Welcome to the Data Science Lab at Phenikaa University!

  • The Data Science Laboratory conducts research in machine learning, artificial intelligence, and its applications to large scale data domains in science and industry. This includes the development of deep generative models, methods for approximate inference, probabilistic programming, Bayesian deep learning, causal inference, reinforcement learning, graph neural networks, and geometric deep learning.
  • The main focus of our research is Automated Machine Learning (AutoML), which includes efficient hyperparameter optimization, neural architecture search, learning to learn, and meta-learning.
  • We also apply AutoML to improve practical deep learning for several applications of high societal importance.
  • While we discuss AutoML in detail on our project webpage AutoML, on this university website we provide information about our publications, teaching, projects, and how to get in touch to start working with us.

# Recent News

  • One of our papers titled “Differentially Private Federated Combinatorial Bandits with Constraints” got accepted in ECML-PKDD 2022
  • Our paper titled “An Autonomous Intelligent Broker for Smart-grids” got accepted in IJCAI, 2022
  • Our paper on “Individual Fairness in Feature-Based Pricing for Monopoly Markets” got accepted in UAI 2022
  • One of our papers titled “Active Learning with BandIt Feedback” got accepted in PAKDD 2022
  • One of our papers on Layered Blockchain protocols got accepted in IEEE ICBC 2022.

# Research

Machine Learning
Information overloaded, dig for interesting patterns!

- Statistical inference
- Hierarchical learning
- Scalable clustering algorithms

Reinforcement Learning
No pain no gain, reinforce yourself but efficiently!

- Adaptive sampling algorithms
- Structured reinforcement learning
- Learning to optimize

Machine Learning with Social Computing
ML is everywhere in our society, make it safe and fair!

- Crowdsourcing system
- Distributed and Federated Learning with Privacy
- Social impact of ML

Graph-Structured Deep Learning
Realize the underlying structure of data!

- Improving graph neural networks
- Drug discovery
- Graph generative models

Large-scale Machine Learning
Find the optima efficiently and robustly!

- Stochastic and distributed optimization methods
- Science of deep learning
- Scalable optimization methods