Jul 2, 2020 · We show that it is possible to flexibly tune the impact of individual losses through a straightforward extension to ERM using a hyperparameter called the tilt.
Jan 12, 2021 · We show that tilted empirical risk minimization (TERM) can be used for enforcing fairness between subgroups, mitigating the effect of outliers, and handling ...
Apr 2, 2021 · Our work explores tilted empirical risk minimization (TERM), a simple and general alternative to ERM, which is ubiquitous throughout machine learning.
People also ask
What is empirical risk minimization?
What is the principle of empirical risk minimization in the context of statistical learning theory?
What is the meaning of risk minimization?
What is the ERM approach in machine learning?
We study a simple extension to ERM---tilted empirical risk minimization (TERM)---which uses exponential tilting to flexibly tune the impact of individual losses ...
Other applications of the TERM framework (e.g., meta-learning, GAN training). ✤ Other properties of TERM (e.g., adversarial robustness).
Empirical risk minimization (ERM) is typically designed to perform well on the average loss, which can result in estimators that are sensitive to outliers, ...
Empirical risk minimization (ERM) is typically designed to perform well on the average loss, which can result in estimators that are sensitive to outliers, ...
This work shows that it is possible to flexibly tune the impact of individual losses through a straightforward extension to ERM using a hyperparameter ...
Empirical risk minimization is a principle in statistical learning theory which defines a family of learning algorithms based on evaluating performance over ...
Jul 12, 2020 · Empirical risk minimization (ERM) is typically designed to perform well on the average loss, which can result in estimators that are ...