In the theory of lossy compression, the rate-distortion (RD) function $ R (D) $ describes how
much a data source can be compressed (in bit-rate) at any given level of fidelity (distortion) …

We consider lossy compression of an information source when the decoder has lossless
access to a correlated one. This setup, also known as the Wyner-Ziv problem, is a special …

This paper studies the fundamental limit of semantic communications over the discrete
memoryless channel. We consider the scenario to send a semantic source consisting of an …

We present a new framework towards the objective of learning coarse-grained models
based on the maximum entropy principle. We show that existing methods for assigning …

This paper proposes a novel methodology for the estimation of the rate distortion function
(RDF) in both continuous and discrete reconstruction spaces. The approach is input-space …

Autoencoders are a popular model in many branches of machine learning and lossy data
compression. However, their fundamental limits, the performance of gradient methods and …

In this paper, we establish novel data-dependent upper bounds on the generalization error
through the lens of a “variable-size compressibility” framework that we introduce newly here …

We formalize the problem of prompt compression for large language models (LLMs) and
present a framework to unify token-level prompt compression methods which create hard …

One-shot channel simulation (or channel synthesis) has seen increasing applications in
lossy compression, differential privacy and machine learning. In this setting, an encoder …

Although deep convolution neural network (DCNN) has achieved great success in computer
vision field, such models are considered to lack interpretability in decision‐making. One of …