Research
Efficient policy optimization is fundamental to solving real-world reinforcement learning problems, where agent-environment interactions can be costly. In this talk, I will discuss my recent research toward improving policy optimization efficiency from the perspective of…
Reinforcement learning carries subtly different meanings in machine learning, cognitive science and neuroscience. In this talk, I will try to clarify in which ways the concepts overlap and in which ways they differ. I will…
We will discuss stochastic processes, Le Jan-Sznitman cascades, that can be associated with certain nonlinear PDE and how explosion of these cascades can be exploited to prove non-uniques for the associated Cauchy problems. In particular,…
The 20th Northwest Probability Seminar, a one-day mini-conference organized by the University of Washington, the Oregon State University, the University of British Columbia, the University of Oregon, and Microsoft Research, was held on October 20,…
Let G be a finite group, and consider the following \emph{product replacement walk} on the set of generating n-tuples of elements of G: randomly pick two of the n elements, say g and h, and…
The (1d) KPZ universality class contains random growth models, directed random polymers, stochastic Hamilton-Jacobi equations (e.g. the eponymous Kardar-Parisi-Zhang equation). It is characterized by unusual scale of fluctuations, some of which appeared earlier in random…
How do you learn programs? View presentation slides here https://new-cm-edgedigital.pages.dev/en-us/research/wp-content/uploads/2018/12/Program-Synthesis-SLIDES.pdf
How do you search over architectures? View presentation slides here https://new-cm-edgedigital.pages.dev/en-us/research/wp-content/uploads/2018/12/Neural-Architecture-Search-SLIDES.pdf
