# Generalization Theory for Through-the-Wall Radar Human Activity Recognition

arXiv: https://arxiv.org/abs/2607.08144 · HTML: https://mlsanity.com/paper/2607.08144/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 46 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [Minimum Excess Risk in Bayesian Learning](https://mlsanity.com/paper/2012.14868/) (2020)
- [Rethinking Domain Generalization: Discriminability and Generalizability](https://mlsanity.com/paper/2309.16483/) (2023)
- [Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization](https://mlsanity.com/paper/2011.02872/) (2020)
- [Empirical Risk Minimization with Relative Entropy Regularization](https://mlsanity.com/paper/2211.06617/) (2022)
- [On the Generalization for Transfer Learning: An Information-Theoretic Analysis](https://mlsanity.com/paper/2207.05377/) (2022)
- [Information-Theoretic Generalization Bounds for Deep Neural Networks](https://mlsanity.com/paper/2404.03176/) (2024)
- [TWR-MCAE: A Data Augmentation Method for Through-the-Wall Radar Human Motion Recognition](https://mlsanity.com/paper/2301.02488/) (2023)
- [Information-Theoretic Analysis of Minimax Excess Risk](https://mlsanity.com/paper/2202.07537/) (2022)
- [Fast Rate Information-theoretic Bounds on Generalization Errors](https://mlsanity.com/paper/2303.14658/) (2023)
- [Through-the-Wall Radar Human Activity Micro-Doppler Signature Representation Method Based on Joint Boulic-Sinusoidal Pendulum Model](https://mlsanity.com/paper/2408.12077/) (2024)
- [How Does Distribution Matching Help Domain Generalization: An Information-theoretic Analysis](https://mlsanity.com/paper/2406.09745/) (2024)
- [RadHARSimulator V1: Model-Based FMCW Radar Human Activity Recognition Simulator](https://mlsanity.com/paper/2509.06751/) (2025)

## Abstract (arXiv)

Through-the-wall radar (TWR) human activity recognition (HAR) is important for non-line-of-sight indoor sensing, security monitoring, and emergency rescue. However, structured distribution shifts caused by person variation, observation-view variation, and wall-condition variation severely degrade recognition generalization, while the origin of the target-domain error still lacks a rigorous theoretical explanation. To address this issue, a generalization-analysis framework for TWR HAR is proposed in this paper. First, models for indoor human kinematics, TWR echo generation, radar image formation, feature representation, and bounded-weight neural networks are established within a unified source-to-target learning formulation. Then, the source risk, target risk, empirical risk, and admissible physical domain descriptor are defined, and a unified target-domain generalization bound is derived. Next, the structured shift term is decomposed into cross-person, cross-view, and cross-wall components, and the bound-tightening effects of physical low-dimensional representations, multi-source training, and parameter-space coverage are analyzed. Simulated and measured experiments jointly support the resulting theoretical analysis and illustrate its application value.