A rank-5 SVD per class plus a Gaussian model of latent coefficients generates replay samples that let A-GEM and Experience Replay match or beat random raw replay at equal memory on MNIST-like datasets and MLP architectures.
Thrun,Lifelong Learning Algorithms, pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Leveraging Lightweight Generators for Memory Efficient Continual Learning
A rank-5 SVD per class plus a Gaussian model of latent coefficients generates replay samples that let A-GEM and Experience Replay match or beat random raw replay at equal memory on MNIST-like datasets and MLP architectures.