3 papers
cs.LG2018
Generalized Batch Normalization: Towards Accelerating Deep Neural Networks
Xiaoyong Yuan, Zheng Feng, Matthew Norton +1
Utilizing recently introduced concepts from statistics and quantitative risk management, we present a general variant of Batch Normalization (BN) that offers accelerated convergenc…
q-fin.RM2018
Calculating CVaR and bPOE for Common Probability Distributions With Application to Portfolio Optimization and Density Estimation
Matthew Norton, Valentyn Khokhlov, Stan Uryasev
Conditional Value-at-Risk (CVaR) and Value-at-Risk (VaR), also called the superquantile and quantile, are frequently used to characterize the tails of probability distribution's an…
stat.ML2017
Optimistic Robust Optimization With Applications To Machine Learning
Matthew Norton, Akiko Takeda, Alexander Mafusalov
Robust Optimization has traditionally taken a pessimistic, or worst-case viewpoint of uncertainty which is motivated by a desire to find sets of optimal policies that maintain feas…