Eigen Memory Trees
Not on the map. Why?
Abstract (arXiv)
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 the OpenML repository in both bounded and infinite memory budget situations.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 37 references that are in the map. First posted on arXiv 25 Oct 2022.
Builds on
14 of 37 references.
References · 14
- 2014OpenML: networked science in machine learningcited by 526
- 2018Online Learning: A Comprehensive Surveycited by 205
- 2017Neural Episodic Controlcited by 151
- 2016Model-Free Episodic Controlcited by 102
- 2016Corralling a Band of Bandit Algorithmscited by 100
- 2018How Complex is your classification problem? A survey on measuring classification complexitycited by 66
- 2018A Contextual Bandit Bake-offcited by 64
- 2018Episodic Memory Deep Q-Networkscited by 42
- 2020Robust High-dimensional Memory-augmented Neural Networkscited by 31
- 2015The Fast Convergence of Incremental PCAcited by 15
- 2018Fast deep reinforcement learning using online adjustments from the pastcited by 14
- 2013Randomized partition trees for exact nearest neighbor searchcited by 12
2 more
- 2017Memory-augmented Neural Machine Translationcited by 12
- 2018Contextual Memory Treescited by 5
Built on by
Not cited yet.