Eigen Memory Trees

Mark Rucker, Jordan T. Ash, John Langford, Paul Mineiro, Ida Momennejad

Keywords: Episodic Memory, Contextual Bandits, Sequential Learning

Abstract: This work introduces the Eigen Memory Tree (EMT), a novel online memory model for sequential learning scenarios. EMTs store data at the leaves of a binary tree, and route new samples through the structure using the principal components of previous experiences, facilitating efficient (logarithmic) access to relevant memories. We demonstrate that EMT outperforms existing online memory approaches, and provide a hybridized EMT-parametric algorithm that enjoys drastically improved performance over purely parametric methods with nearly no downsides. Our findings are validated using 206 datasets from OpenML repository in both bounded and infinite memory budget situations.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)

TL;DR: We create an episodic memory model for online learning and evaluate it for solving contextual bandit problems.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/eigen-memory-trees/code)