Speaker: Jacob Scott Laurel
Abstract: As Edge and IoT computing devices process noisy data or make decisions in uncertain environments, they require frameworks for inexpensive, yet accurate probabilistic inference. Probabilistic programming has emerged as a powerful way for developers to write high-level programs, while abstracting away the implementation details of inference. However, the existing algorithms are slow and often assumed to require precise calculations. We present Statheros, the first compiler for low-level, fixed-point approximation of probabilistic programming. Statheros compiles programs to fixed-point inference procedures and is able to determine the optimal fixed-point type to use. We evaluate Statheros on 13 benchmarks and three embedded platforms. The results show that Statheros-generated code is 11.5x (Arduino), 3.8x (PocketBeagle), and 2.2x (Raspberry Pi) faster than single-precision floating-point computation, with minimal accuracy loss.
Bio: Jacob is a 5th year CS PhD student working with Prof. Sasa Misailovic on Probabilistic Programming, Approximate Computing, and more recently static analysis of Neural Networks.
