Lightweight Representation Learning for Low Tucker Rank Tensors
Low Tucker rank tensors provide compact representations of multidimensional dependencies, but standard learning pipelines can incur substantial computational and memory overhead from redundant intermediate quantities. We reduce this overhead without modifying the underlying representation objective or parameterization. Our approach combines three complementary components: (i) sequential…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
