|
Reza Asad I’m a machine learning researcher specializing in reinforcement learning, currently transitioning to industry research. I completed my PhD at Simon Fraser University, where I was co-advised by Sharan Vaswani and Manolis Savva. During my PhD, I completed research internships at Microsoft and Amazon, working on policy optimization and preference learning. Previously, I worked as a data scientist in the San Francisco Bay Area for three years and as a research and teaching assistant in Applied Mathematics at the University of British Columbia. I hold a Bachelor’s degree in Pure Mathematics from the University of Toronto. |
|
ResearchMy research interests span policy optimization, exploration, and LLM post-training through RLHF and RLVR. I design and analyze reinforcement learning objectives and algorithms for on-policy and off-policy settings, aiming to combine theoretical rigor with strong empirical performance. |
Papers
Optimistic Actor-Critic with Parametric Policies: Unifying Sample Efficiency and Practicality
Reza Asad, Reza Babanezhad, Sharan Vaswani NeurIPS Workshop on Aligning Reinforcement Learning Experimentalists and Theorists (ARLET), 2025.
Fast Convergence of Softmax Policy Mirror Ascent
Surrogate Minimization: An Optimization Algorithm for Training Large Neural Networks with Model Parallelism
3DSSR: 3D Subscene Retrieval
Steiner symmetrization along a certain equidistributed sequence of directions
Cloudmaskgan: A content-aware unpaired image-to-image translation algorithm for remote sensing imagery
Embedded eigenvalues and the nonlinear Schrödinger equation
|