Establishes nonasymptotic achievability for the information bottleneck channel with fixed- and variable-length relaying and introduces a novel variable-length noisy lossy source coding bound.
Channel simulation: Theory and applications to lossy compression and differential privacy
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.IT 3verdicts
UNVERDICTED 3representative citing papers
SoftBinary Coding uses a stochastic binary latent space and a novel rate-optimal binary channel simulation to address train-test mismatch and smoothness bias in neural compression, with experimental gains over NTC and SOTA vector quantization results.
A game-theoretic information theory with dynamic hedging and nonconvex downward-closed cones subsumes probabilistic channel coding theorems and adversarial settings.
citing papers explorer
-
Nonasymptotic Oblivious Relaying and Variable-Length Noisy Lossy Source Coding
Establishes nonasymptotic achievability for the information bottleneck channel with fixed- and variable-length relaying and introduces a novel variable-length noisy lossy source coding bound.
-
SoftBinary Coding: A New Information-Theoretic Neural Compression Paradigm
SoftBinary Coding uses a stochastic binary latent space and a novel rate-optimal binary channel simulation to address train-test mismatch and smoothness bias in neural compression, with experimental gains over NTC and SOTA vector quantization results.
-
A Non-Probabilistic Game-Theoretic Information Theory Which Subsumes Probabilistic Channel Coding
A game-theoretic information theory with dynamic hedging and nonconvex downward-closed cones subsumes probabilistic channel coding theorems and adversarial settings.