# Semantic Communication of Learnable Concepts

arXiv: https://arxiv.org/abs/2305.08126 · HTML: https://mlsanity.com/paper/2305.08126/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 14 May 2023.

## Builds on (most cited first, 9 of 9)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Information-theoretic analysis of generalization capability of learning algorithms](https://mlsanity.com/paper/1705.07809/) (2017)
- [Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications](https://mlsanity.com/paper/2207.09353/) (2022)
- [Reasoning About Generalization via Conditional Mutual Information](https://mlsanity.com/paper/2001.09122/) (2020)
- [Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters](https://mlsanity.com/paper/1810.00440/) (2018)
- [The Information Complexity of Learning Tasks, their Structure and their Distance](https://mlsanity.com/paper/1904.03292/) (2019)
- [Algorithms for the Communication of Samples](https://mlsanity.com/paper/2110.12805/) (2021)
- [On statistical learning via the lens of compression](https://mlsanity.com/paper/1610.03592/) (2016)
- [Rate-Constrained Remote Contextual Bandits](https://mlsanity.com/paper/2204.12620/) (2022)

## Built on by (most cited first, 2 of 2)

- [Effective Communication with Dynamic Feature Compression](https://mlsanity.com/paper/2401.16236/) (2024)
- [Minimal Communication-Cost Statistical Learning](https://mlsanity.com/paper/2406.08193/) (2024)

## Abstract (arXiv)

We consider the problem of communicating a sequence of concepts, i.e., unknown and potentially stochastic maps, which can be observed only through examples, i.e., the mapping rules are unknown. The transmitter applies a learning algorithm to the available examples, and extracts knowledge from the data by optimizing a probability distribution over a set of models, i.e., known functions, which can better describe the observed data, and so potentially the underlying concepts. The transmitter then needs to communicate the learned models to a remote receiver through a rate-limited channel, to allow the receiver to decode the models that can describe the underlying sampled concepts as accurately as possible in their semantic space. After motivating our analysis, we propose the formal problem of communicating concepts, and provide its rate-distortion characterization, pointing out its connection with the concepts of empirical and strong coordination in a network. We also provide a bound for the distortion-rate function.