Winnie Xu, Matthew J Muckley, Yann Dubois, Karen Ullrich

An interesting problem in representation learning is training on an optimal index that is helpful towards the learning task. We explore the impacts of sequentially compressing an unordered set of assets as opposed to random priority assignment. Unfortunately, general set compression methods show minimal gains in terms of rate-distortion tradeoff when used with our proposed associative compression architectures.

ICLR Neural Compression Workshop, 2023.

Paper