معرفی
Gaurav Mahajan serves as a Postdoctoral Associate in Yale University's Department of Computer Science under Dan Spielman's mentorship, concurrently holding lecturer appointments for specialized courses including CPSC 648: Quantum Codes (Fall 2024) and the ICTS Reinforcement Learning Theory Bootcamp (Fall 2025). His academic journey includes a PhD from UCSD's Theory Group advised by Sanjoy Dasgupta and Shachar Lovett, with research summers at Microsoft Research, Institute for Advanced Study, and Simons Institute.
His research spans machine learning theory with dual emphases on quantum learning (quantum error correction applications to complexity theory) and reinforcement learning (computational-statistical gaps, sample complexity). Recent publications in COLT, ALT, and NeurIPS reveal a trajectory from foundational PAC learning theory toward quantum-enhanced complexity analysis, featuring collaborations with leading theorists including Sham Kakade, Shachar Lovett, and Daniel Kane.
Teaching activities demonstrate specialized expertise: his Quantum Codes course progresses from basic stabilizer codes to quantum Tanner codes using chain complex formalisms, while the RL Bootcamp bridges PyTorch implementations with theoretical complexity analysis. Though not leading a formal lab, his work connects Yale's quantum initiative with theoretical computer science communities through institutes like Simons.
Current research shows increasing focus on quantum-classical connections—applying quantum information tools (e.g., classical shadows) to classical learning problems—while maintaining rigorous theoretical standards evidenced by consistent publications in top theory venues. Future directions likely involve deeper quantum complexity applications and expanding the quantum-RL interface.
