Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss
This paper studies a risk minimization problem with decision dependent data distribution.
The problem pertains to the performative prediction setting where a trained model can affect …
The problem pertains to the performative prediction setting where a trained model can affect …
Zeroth-Order Methods for Nonconvex Stochastic Problems with Decision-Dependent Distributions
Y Hikima, A Takeda - arXiv preprint arXiv:2412.20330, 2024 - arxiv.org
In this study, we consider an optimization problem with uncertainty dependent on decision
variables, which has recently attracted attention due to its importance in machine learning …
variables, which has recently attracted attention due to its importance in machine learning …
Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss
LI Qiang, HT Wai - The Thirty-eighth Annual Conference on Neural … - openreview.net
This paper studies a risk minimization problem with decision dependent data distribution.
The problem pertains to the performative prediction setting in which a trained model can …
The problem pertains to the performative prediction setting in which a trained model can …