all AI news
Optimizing the Performative Risk under Weak Convexity Assumptions. (arXiv:2209.00771v1 [cs.LG])
Sept. 5, 2022, 1:13 a.m. | Yulai Zhao
stat.ML updates on arXiv.org arxiv.org
In performative prediction, a predictive model impacts the distribution that
generates future data, a phenomenon that is being ignored in classical
supervised learning. In this closed-loop setting, the natural measure of
performance, denoted the performative risk, captures the expected loss incurred
by a predictive model after deployment. The core difficulty of minimizing the
performative risk is that the data distribution itself depends on the model
parameters. This dependence is governed by the environment and not under the
control of the …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Social Insights & Data Analyst (Freelance)
@ Media.Monks | Jakarta
Cloud Data Engineer
@ Arkatechture | Portland, ME, USA