MLLGFeb 25, 2021

On regret bounds for continual single-index learning

arXiv:2102.12961v21 citations
Originality Synthesis-oriented
AI Analysis

This work addresses continual learning challenges for researchers in online and transfer learning, but it appears incremental as it extends existing single-index models to a new setting without broad SOTA claims.

The paper tackles the problem of generalizing single-index models to continual learning, where tasks arrive sequentially with online data, by proposing a randomized strategy that learns a common single-index for all tasks and task-specific link functions, resulting in proven regret bounds under various loss function assumptions.

In this paper, we generalize the problem of single-index model to the context of continual learning in which a learner is challenged with a sequence of tasks one by one and the dataset of each task is revealed in an online fashion. We propose a randomized strategy that is able to learn a common single-index (meta-parameter) for all tasks and a specific link function for each task. The common single-index allows to transfer the information gained from the previous tasks to a new one. We provide a rigorous theoretical analysis of our proposed strategy by proving some regret bounds under different assumption on the loss function.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes