Research Interests
My research interests lie in providing mathematical and theoretical foundations to justify and understand (deep) machine learning models and designing efficient learning algorithms for problems in computer vision and data mining, with a particular emphasis on
Weakly supervised deep learning (e.g., deep transfer learning and learning with label noise)

Deep adversarial learning (e.g., adversarial attack and defense)
Deep unsupervised learning (e.g., clustering and matrix factorisation)
Image and video processing (e.g., deep classification algorithms)
Statistical deep learning theory (e.g., hypothesis complexity and generalisation error)