MLSP-L19.4
Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networks
Sanket Jantre, Nathan M. Urban, Xiaoning Qian, Byung-Jun Yoon, Brookhaven National Laboratory, United States of America
Session:
MLSP-L19: Bayesian Machine Learning Lecture
Track:
Machine Learning for Signal Processing
Location:
Room E2
Presentation Time:
Thu, 18 Apr, 17:30 - 17:50 (UTC +9)
Session Co-Chairs:
Feng Yin, Chinese University of Hong Kong and Peter Gerstoft, University of California San Diego
Session MLSP-L19
MLSP-L19.1: BAYESIAN OPTIMIZATION WITH GAUSSIAN PROCESSES FOR ROBUST LOCALIZATION
William Jenkins, Peter Gerstoft, University of California San Diego, United States of America
MLSP-L19.2: A NOVEL ARCHITECTURE OF DEEP FEATURE-BASED GAUSSIAN PROCESSES WITH AN ENSEMBLE OF KERNELS
Yuanqing Song, Yuhao Liu, Petar Djuric, Stony Brook University, United States of America
MLSP-L19.3: RANDOMIZED MAXIMUM LIKELIHOOD VIA HIGH-DIMENSIONAL BAYESIAN OPTIMIZATION
Valentin Breaz, Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP*, LJK, France; Richard Wilkinson, University of Nottingham, United Kingdom of Great Britain and Northern Ireland
MLSP-L19.4: Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networks
Sanket Jantre, Nathan M. Urban, Xiaoning Qian, Byung-Jun Yoon, Brookhaven National Laboratory, United States of America
MLSP-L19.5: IMPROVING OPEN-SET RECOGNITION WITH BAYESIAN METRIC LEARNING
Tong Chen, Guanchao Feng, Petar Djuric, Stony Brook University, United States of America
MLSP-L19.6: SUNFLOWER STRATEGY FOR BAYESIAN RELATIONAL DATA ANALYSIS
Masahiro Nakano, Ryohei Shibue, Kunio Kashino, NTT Communication Science Laboratories, Japan
Contacts