TU2.R1.1

Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning

Gil I. Shamir, Google, United States; Wojciech Szpankowski, Purdue University, United States
Session:
Bayesian estimation
Track:
8: Learning Theory
Location:
Ballroom II & III
Presentation Time:
Tue, 9 Jul, 11:30 - 11:50
Session Chair:
Wojtek Szpankowski, Purdue Univeristy
Presentation
Not logged in.
Discussion
Not logged in.
Session TU2.R1
TU2.R1.1: Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning
Gil I. Shamir, Google, United States; Wojciech Szpankowski, Purdue University, United States
TU2.R1.2: Personalized heterogeneous Gaussian mean estimation under communication constraints
Ruida Zhou, Suhas Diggavi, University of California Los Angeles, United States
TU2.R1.3: Multivariate Priors and the Linearity of Optimal Bayesian Estimators under Gaussian Noise
Leighton Barnes, Center for Communications Research, United States; Alex Dytso, Qualcomm, United States; Jingbo Liu, University of Illinois, United States; H Vincent Poor, Princeton University, United States
TU2.R1.4: Bayesian Persuasion: From Persuasion toward Counter-suasion
Ananya Das, IIT Kharagpur, India; Aishwarya Soni, Independent researcher, India; Amitalok Budkuley, IIT Kharagpur, India
Resources
No resources available.