joaompereira Goto Github PK

I'm an Assistant Professor in the Instituto de Matemática Pura e Aplicada. I am an applied mathematician studying machine learning, multi-linear algebra and information theory. My research centers on scalable methods and statistical fundamental limits of high-dimensional inverse problems, that include tensor decomposition, cryo-electron microscopy, and partial and stochastic differential equations. In addition, I have interests in machine learning, deep learning, statistics, information theory and optimization.

​I was a Ph.D. student of Emmanuel Abbe and Amit Singer at Princeton University and worked as a postdoc with Vahid Tarokh at Duke University, and with Joe Kileel and Rachel Ward at University of Texas at Austin.

Some interesting Github repositories I have authored or helped out:

• Implementation of the subspace power method for tensor decomposition (in MATLAB and Python)
• Implementation of several works using PINNs for equation discovery, together with Ali Hasan
• A little bit of a fun side-project, I developed a solver for Wordle (a game of NY Times)
• Expect new scalable algorithms for several inverse problems coming here