A broad goal of computational complexity theory is to understand the limits of efficient computation in a variety of models. Apart from being a natural and fascinating field of study in its own right, computational complexity has actively contributed to artificial intelligence and machine learning, computational biology, mathematics, quantum physics, and other disciplines. Over the course of my doctoral studies, I have solved several longstanding open problems in computational complexity, notably in the challenging area of communication complexity. I have also developed a body of novel analytic methods that have enabled substantial progress in the field by other researchers, with 5 new papers by 9 different authors crucially building on my work over the past year alone. Finally, I have consistently complemented my research in computational complexity with important contributions in learning theory and, more recently, quantum computing. I look forward to maintaining and cultivating this interdisciplinary dimension of my academic career. My work has repeatedly received recognition in the research community, with 3 “Best Student Paper” awards at premier conferences, 10 invited talks at top universities and workshops, an invited survey article in the widely read Bulletin of the European Association for Theoretical Computer Science, and extended research visits to Columbia University and the Institute for Advanced Study (Princeton, NJ). In the remainder of this research statement, I will present my accomplishments in computational complexity and learning