Continual learning empowers models to adapt autonomously to the ever-changing
environment or data streams without forgetting old knowledge. Prompt-based approaches …

The incremental learning paradigm in machine learning has consistently been a focus of
academic research. It is similar to the way in which biological systems learn, and reduces …

The goal of continual learning (CL) is to continuously learn new tasks without forgetting
previously learned old tasks. To alleviate catastrophic forgetting, gradient projection based …

The goal of continual learning (CL) is to learn from a series of continuously arriving new
tasks without forgetting previously learned old tasks. To avoid catastrophic forgetting of old …

Reinforcement learning in general unstructured MDPs presents a challenging learning
problem. However, certain MDP structures, such as factorization, are known to simplify the …

Backward compatibility of model predictions is a desired property when updating a machine
learning driven application. It allows to seamlessly improve the underlying model without …

Continual learning is inherently a constrained learning problem. The goal is to learn a
predictor under a no-forgetting requirement. Although several prior studies formulate it as …

In many real-world settings, regulations and economic incentives permit the sharing of
models but not data across institutional boundaries. In such scenarios, practitioners might …

The loss function plays an important role in optimizing the performance of a learning system.
A crucial aspect of the loss function is the assignment of sample weights within a mini-batch …

The notion of generalization has moved away from the classical one defined in statistical
learning theory towards an emphasis on out-of-domain generalization (OODG). Recently …