Ph.D. in

This course provides an advanced course on probability theory and stochastic processes essential for modeling a variety of real-world scenarios involving uncertainty and randomness. Students will become experts in the language of probability theory, enabling them to effectively analyze and address complex challenges in both pure and applied sciences. Through practical problem solving, they will harness the power of probabilistic thinking to derive insightful solutions.

This course explores statistics based on the principles of probability theory. It takes an in-depth look at the mathematical foundations of decision theory and provides students with tools and techniques for constructing estimators, hypothesis tests, and confidence regions. The course also focuses on the exploration of empirical process theory, emphasizing key optimality results of likelihood methods. In addition, the course highlights several key areas of statistics, such as resampling techniques and nonparametric statistics.

This course delves into the theoretical core of statistical learning through a rigorous exploration of algorithmic paradigms, statistical learning frameworks, and optimization strategies. This course provides a principled foundation, enriched by the study of high-dimensional probability and statistics, preparing students to navigate and innovate within the statistical learning landscape.

This course prepares PhD students to tackle scientific questions using data within the modern data science life cycle. It emphasizes critical thinking, computational methodology, and trustworthy, reproducible practices. Through open-ended labs in Python students will explore exploratory data analysis, model formulation and validation, simulation, and interpretation, while critically examining the assumptions underpinning standard statistical models and methods. The class will culminate in a group project.

This course is designed to explore recent breakthroughs in machine learning and provide students with the necessary skills to conduct research and advance the field of machine learning. It will cover highly specialized topics related to large-scale optimization for real-world problems, including Large-Scale Training of Kernel Methods, Sparse Learning, Bilevel Optimization, Black Box Optimization, and Spiking Neural Networks. Prior knowledge of fundamental concepts in machine learning, optimization, and statistics is assumed.

The course covers advanced topics in continuous optimization, such as stochastic gradient descent and its variants, methods that use more than first-order information, primal-dual methods, and methods for composite problems. Participants will read the current state-of-the-art relevant literature and prepare presentations to the other students. Participants will explore how the presented methods work for optimization problems that arise in various fields of Machine Learning and test them in real-world optimization formulations to get a deeper understanding of the challenges being discussed.

The course covers advanced topics in Reinforcement Learning (RL). Participants will read the current state-of-the-art relevant literature and prepare presentations to the other students. Participants will explore how the presented methods work in simplified computing environments to get a deeper understanding of the challenges that are being discussed. Topics discussed include exploration, imitation learning, hierarchical RL, multi agent RL in both competitive and collaborative setting. The course will also explore multitask and transfer learning in RL setting.

This is a graduate course in a new branch of machine learning: federated learning (FL). In FL, machine learning models are trained on mobile devices with an explicit effort to preserve the privacy of users’ data. FL combines supervised machine learning, privacy, distributed and edge computing, optimization, communication compression, and systems. This is a new and fast-growing field with few theoretical results and early production systems (e.g., Tensor Flow Federated and FedML). This course aims for students to become familiar with the field’s key developments and practices, namely optimization methods for FL and techniques to address communication bottlenecks, systems and data heterogeneities, client selection, robustness, fairness, personalization and privacy aspects of FL. The evaluation of the course heavily relies on students’ paper presentations and the final project selected by the student.

In the past decades, interesting advances were made in machine learning, philosophy, and statistics for tackling long-standing causality problems, including how to discover causal knowledge from observational data, known as causal discovery, and how to infer the effect of interventions. Furthermore, it has recently been shown that the causal perspective may facilitate understanding and solving various machine learning / artificial intelligence problems such as transfer learning, semi-supervised learning, out-of-distribution prediction, disentanglement, and adversarial vulnerability. This course is concerned with understanding causality, learning causality from observational data, and using causality to tackle a large class of learning problems. The course will include topics like graphical models, causal inference, causal discovery, and counterfactual reasoning. It will also discuss how we can learn causal representations, perform transfer learning, and understand deep generative models.

This course is an advanced course on algorithms for big data that involves the use of randomized methods, such as sketching and sampling, to provide dimensionality reduction. It also discussed topics such as Sub-space Embeddings, Low rank Approximation, L1 Regression, Data Streams. The course lies at the intersection of machine learning and statistics.

This course focuses on building foundations and introducing recent advances in dimensionality reduction and manifold learning, important topics in machine learning. This course builds upon fundamental concepts in machine learning and additionally assumes familiarity with concepts in optimization and mathematics. The course covers advanced topics in spectral, probabilistic, and neural network-based dimensionality reduction and manifold learning. Students will be engaged through coursework, assignments, and projects.

This course prepares PhD students to tackle scientific questions using data within the modern data science life cycle. It emphasizes critical thinking, computational methodology, and trustworthy, reproducible practices. Through open-ended labs in Python students will explore exploratory data analysis, model formulation and validation, simulation, and interpretation, while critically examining the assumptions underpinning standard statistical models and methods. The class will culminate in a group project.

Deep Learning (DL) is an extremely important applied science that, at present, is poorly understood theoretically. We know that neural networks work well but cannot fully explain why. Nevertheless, in recent years, there has been a rapid growth of publications that shed light on the new mathematics underlying DL, and we see now many interesting connections between DL and various other fields, e.g., approximation theory, differential equations, information theory, random matrix theory, statistical physics. This course aims to introduce students to these cutting-edge developments.

High dimensional Probability investigates the behavior of high dimensional random objects, such as random vectors, random matrices with the emphasis upon quantifying the role of the dimension. The course also introduces some contemporary statistical problems, including principal component analysis in high-dimension, sparse linear regression, community detection.

This course will prepare students to produce professional-quality research and solve a practical research challenge in an organization based on an innovative, sustainable, and entrepreneurial research topic. This course will provide exposure to a variety of special topics, research integrity, ethics, organizational challenges, and needs related to various disciplines. Students will design and implement a research project suitable for conference presentation or journal submission relevant to their field of interest, in addition to peer-reviewing a paper. The instructor, and guest lecturers, as appropriate, will present topics necessary to develop well-rounded researchers, innovators, and entrepreneurs in the AI disciplines.

PhD in Statistics and Data Science thesis research exposes students to cutting-edge and unsolved research problems, where they are required to propose new solutions and significantly contribute towards the body of knowledge. Students pursue an independent research study, under the guidance of a supervisory panel, for a period of 3 to 4 years. PhD thesis research helps train graduates to become leaders in their chosen area of research through partly supervised study, eventually transforming them into researchers who can work independently or interdependently to carry out cutting edge research.

The MBZUAI internship with industry is intended to provide the student with hands-on experience, blending practical experiences with academic learning. For PhD students the internship should be 3 months in length. Hours should align with the working hours of the host organization and the internship should directly relate to the student’s research at MBZUAI.