Alhad is a final-year undergraduate student with a strong passion for learning theory and statistics, particularly in the application of information-theoretic tools. His previous research has concentrated on upper bounds on the generalisation error of learning algorithms. Recently, he developed an interest in lower bounds for learning and statistical inference, delving into the fundamental trade-off between sample size and memory usage in algorithms. Over the past decade, seminal works have established robust, unconditional lower bounds for complex problems, such as learning parities. This area sits at the intersection of information theory and statistics, often employing techniques from rate distortion theory and coding theory to achieve impressive results. Additionally, Alhad is keen to explore learning under various privacy constraints, specifically through the lens of differential privacy, which provides a solid framework for understanding privacy implications in statistical learning.