5 papers
Understanding Rate-Distortion Performance in Distributed Transformer Inference
Anderson de Andrade, Alon Harell, Ivan V. BajiÄ
Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference. This inference can be made more efficient by partitionin…
Lossy Common Information in a Learnable Gray-Wyner Network
Anderson de Andrade, Alon Harell, Ivan V. BajiÄ
Many computer vision tasks share substantial overlapping information, yet conventional codecs tend to ignore this, leading to redundant and inefficient representations. The Gray-Wy…
Mutual Information Bounds for Lossy Common Information
Anderson de Andrade
We show the mutual information between the targets in a Gray-Wyner Network as a bound that separates Wyner's lossy common information and Gács-Körner lossy common information. Th…
Rate-Distortion Theory in Coding for Machines and its Application
Alon Harell, Yalda Foroutan, Nilesh Ahuja +6
Recent years have seen a tremendous growth in both the capability and popularity of automatic machine analysis of images and video. As a result, a growing need for efficient compre…
Towards Task-Compatible Compressible Representations
Anderson de Andrade, Ivan BajiÄ
We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a diff…