Online Multitask Learning with Long-Term Memory

Authors: Mark Herbster, Stephen Pasteris, Lisa Tse

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We introduce a novel online multitask setting. In this setting each task is partitioned into a sequence of segments that is unknown to the learner. Associated with each segment is a hypothesis from some hypothesis class. We give algorithms that are designed to exploit the scenario where there are many such segments but significantly fewer associated hypotheses. We prove regret bounds that hold for any segmentation of the tasks and any association of hypotheses to the segments. In the single-task special case this is the first example of an efficient regret-bounded switching algorithm with long-term memory for a non-parametric hypothesis class. We provide an algorithm that predicts on each trial in time linear in the number of hypotheses when the hypothesis class is finite. We also consider infinite hypothesis classes from reproducing kernel Hilbert spaces for which we give an algorithm whose per trial time complexity is cubic in the number of cumulative trials.
Researcher Affiliation Academia Mark Herbster, Stephen Pasteris, Lisa Tse Department of Computer Science University College London London United Kingdom (m.herbster|s.pasteris|l.tse)@cs.ucl.ac.uk
Pseudocode Yes Algorithm 1 Predicting Hfi n in a switching multitask setting. Algorithm 2 Predicting H(x) K in a switching multitask setting.
Open Source Code No The paper does not contain any explicit statements or links indicating that source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not describe experiments using datasets for training.
Dataset Splits No The paper is theoretical and does not describe experiments with dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe experiments, thus no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe experiments or their implementation details with specific software versions.
Experiment Setup No The paper is theoretical and does not describe experiments or their setup, including hyperparameters.