Regression Models

Unveiling Insights from "Gradient Descent Converges Linearly for Logistic Regression on Separable Data"

Bang An, Ph.D. Student, Applied Mathematics and Computational Sciences

Jan 17, 10:00 - 11:00

B1 L0 R0118

gradient methods Regression Models

Abstract In this presentation, I will share a paper titled "Gradient Descent Converges Linearly for Logistic Regression on Separable Data", a work highly related to my ongoing research. I will explore its relevance to my current research topic and discuss the inspiration for our future works. Abstract of the paper: We show that running gradient descent with variable learning rate guarantees loss f(x) \leq 1.1f(x^*)+\epsilon for the logistic regression objective, where the error \epsilon decays exponentially with the number of iterations and polynomially with the magnitude of the entries of an

Wagner Barreto-Souza

Research Scientist, Statistics

Time Series Survival analysis Regression Models Applied Probability

Wagner Barreto-Souza is a Research Scientist of the KAUST Biostatistics Group headed by Prof. Hernando Ombao. Early Career Professor of Statistics, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil. (2013-2020) Education Profile Ph.D. in Statistics. Universidade de São Paulo, SP, Brazil. (2012) M.S. in Statistics. Universidade Federal de Pernambuco, Recife, Brazil. (2008) B.S. in Statistics. Universidade Federal de Pernambuco, Recife, Brazil. (2006)