Mark Tygert

Research Scientist

Positions prior to Facebook Artificial Intelligence Research were on the faculty at NYU’s Courant Institute, UCLA, and Yale, following undergraduate, graduate, and postdoctoral studies at Princeton and Yale. Research focuses have included fast spherical harmonic transforms, randomized algorithms for linear algebra, and complements to chi-square tests. Recent honors include the 2010 William O. Baker Award from the U.S. National Academy of Sciences and a 2012 DARPA Young Faculty Award.


Computational science and statistics

Latest Publications

Journal of Big Data - November 6, 2021

A graphical method of cumulative differences between two subpopulations

Mark Tygert

Journal of Big Data - July 19, 2021

Cumulative deviation of a subpopulation from the full population

Mark Tygert

Information and Inference: a Journal of the IMA - January 18, 2021

Secure multiparty computations in floating-point arithmetic

Chuan Guo, Awni Hannun, Brian Knott, Laurens van der Maaten, Mark Tygert, Ruiyu Zhu

PLOS ONE - December 3, 2019

A hierarchical loss and its problems when classifying non-hierarchically

Cinna Wu, Mark Tygert, Yann LeCun

SIAM Journal on Matrix Analysis and Applications - December 17, 2018

Regression-aware decompositions

Mark Tygert

ArXiv - June 25, 2015

Scale-Invariant Learning and Convolutional Networks

Mark Tygert, Arthur Szlam, Soumith Chintala, Marc'Aurelio Ranzato, Yuandong Tian, Wojciech Zaremba

ArXiv - June 22, 2015

A Theoretical Argument for Complex-Valued Convolutional Networks

Joan Bruna, Soumith Chintala, Yann LeCun, Serkan Piantino, Arthur Szlam, Mark Tygert

ArXiv - June 22, 2015

An Implementation of a Randomized Algorithm for Principal Component Analysis

Arthur Szlam, Mark Tygert, Yuval Kluger