First-order Optimization for Superquantile-based Supervised Learning
Classical supervised learning via empirical risk (or negative log-likelihood) minimization hinges upon the assumption that the testing distribution coincides with the training distribution. This assumption can be challenged in modern applications of machine learning in which learning machines may operate at prediction time with testing data whose distribution departs from the one of the training data. We revisit the superquantile regression method by proposing a first-order optimization algorithm to minimize a superquantile-based learning objective. The proposed algorithm is based on smoothing the superquantile function by infimal convolution. Promising numerical results illustrate the interest of the approach towards safer supervised learning.
Code (1)
Tasks
BIG-bench Machine LearningregressionSimilar Papers 제목 키워드 기반
Fast Computation of Superquantile-Constrained Optimization Through Implicit Scenario Reduction
Superquantiles have recently gained significant interest as a risk-aware metric for addressing fairness and distribution shifts in statistical learning and decision making problems. This paper introduces a fast, scalable…
FairnessCalculating CVaR and bPOE for Common Probability Distributions With Application to Portfolio Optimization and Density Estimation
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 and are popular measures of risk. Buffered…
Density EstimationPortfolio OptimizationDevice Heterogeneity in Federated Learning: A Superquantile Approach
We propose a federated learning framework to handle heterogeneous client devices which do not conform to the population data distribution. The approach hinges upon a parameterized superquantile-based objective, where the…
Federated LearningThe Risk Quadrangle in Optimization: An Overview with Recent Results and Extensions
This paper revisits and extends the 2013 development by Rockafellar and Uryasev of the Risk Quadrangle (RQ) as a unified scheme for integrating risk management, optimization, and statistical estimation. The RQ features f…
Portfolio OptimizationFederated Learning with Superquantile Aggregation for Heterogeneous Data
We present a federated learning framework that is designed to robustly deliver good predictive performance across individual clients with heterogeneous data. The proposed approach hinges upon a superquantile-based learni…
Federated Learning