In an era dominated by digital interactions and data-driven decision-making, the influence of
Artificial Intelligence (AI) on personalized content marketing has become a focal point of …

Test-time adaptation (TTA) adapts a source model to the distribution shift in testing data
without using any source data. There have been plenty of algorithms concentrated on …

We investigate online convex optimization in non-stationary environments and choose
dynamic regret as the performance measure, defined as the difference between cumulative …

We study the problem of Online Convex Optimization (OCO) with memory, which allows loss
functions to depend on past decisions and thus captures temporal effects of learning …

Dealing with distribution shifts is one of the central challenges for modern machine learning.
One fundamental situation is the covariate shift, where the input distributions of data change …

The stochastically extended adversarial (SEA) model, introduced by Sachs et al.(2022),
serves as an interpolation between stochastic and adversarial online convex optimization …

This paper focuses on supervised and unsupervised online label shift, where the class
marginals $ Q (y) $ variesbut the class-conditionals $ Q (x| y) $ remain invariant. In the …

Conversion rate (CVR) prediction is one of the core components in online recommender
systems, and various approaches have been proposed to obtain accurate and well …

Online control with non-stochastic disturbances and adversarially chosen convex cost
functions, referred to as online non-stochastic control, has recently attracted increasing …

In many real-world applications, data are continuously accumulated within open
environments. For instance, in disease diagnosis, the prevalence of diseases can vary …