Machine Learning
Research Group
Advancing the frontiers of General Machine Learning, Deep Learning Models, and High-dimensional Statistics
Research Areas
Our interdisciplinary research spans multiple domains of deep learning
General Machine Learning
Clustering Algorithms, Optimization Techniques, and theoretical foundations of machine learning systems.
Deep Learning Models
GAN, VAE, Transformers, and Topological Deep Learning Models.
High-dimensional Statistics
Statistical methods for high-dimensional data analysis, Causal Inference and Optimal Transport.
Model Expressivity
Understanding the representational capacity and theoretical limits of neural networks.
AI Applications
Real-world applications of AI in various domains including Healthcare.
Research Impact
Numbers that reflect our commitment to advancing machine learning research
Research Scholars
Publications
Years Active
Grad Students
Featured Publications
Highlighting our prominent Works at some pretigious venues
Information preservation with wasserstein autoencoders: generation consistency and adversarial robustness
Amongst the numerous variants Variational Autoencoder (VAE) has inspired, the Wasserstein Autoencoder (WAE) stands out due to its heightened generative quality and intriguing theoretical properties. ...
Algorithmic Fairness in Lesion Classification by Mitigating Class Imbalance and Skin Tone Bias
Deep learning models have shown considerable promise in the classification of skin lesions. However, a notable challenge arises from their inherent bias towards dominant skin tones and the issue ...
Enhancing Contrastive Clustering with Negative Pair-guided Regularization
Contrastive Learning (CL) aims to create effective embeddings for input data by minimizing the distance between positive pairs, i.e., different augmentatiobs orviews of the same sample. To avoid ...