Yaniv Plan

Yaniv Plan is an Associate Professor of Mathematics at the University of British Columbia. His research focuses on applied probability, compressive sensing, matrix completion, and mathematical foundations of machine learning. He co-organizes the interdisciplinary group Mathematics of Information, Learning, and Data (MILD). His work bridges high-dimensional probability with applications in signal processing and data science.

He teaches advanced courses such as Probability in High Dimensions and Compressed Sensing, emphasizing theoretical foundations like concentration inequalities, random matrix theory, and optimization. His research has led to advancements in 1-bit compressed sensing, matrix completion, and robust recovery algorithms. Notably, he received the NIPS 2018 Best Paper Award for contributions to learning Gaussian mixtures via sample compression.

Plan’s publications address topics like sub-Gaussian matrices, weighted matrix completion, and non-smooth stochastic gradient descent. His work often combines rigorous mathematical analysis with practical applications in compressed sensing and sparse recovery.

He collaborates widely, with co-authors including Roman Vershynin, Emmanuel Candès, and Mary Wootters. His research has been supported by grants exploring compressed sensing, high-dimensional data, and algorithmic robustness.