{
  "annotation_id": "0cfbb671-de2c-4c1b-825b-95bd329a1365",
  "date_created": "2026-02-17T05:53:05.015000Z",
  "date_modified": "2026-02-17T05:53:05.015000Z",
  "file_hash": "589fc2a0630414c0f8abfe525878f17d75e00bd79ded1648f74d3324ba25d795",
  "private": false,
  "record": {
    "abstract": "Neural networks have shown state-of-the-art performances in various classification and regression tasks. Rectified linear units (ReLU) are often used as activation functions for the hidden layers in a neural network model. In this article, we establish the connection between the Poisson hyperplane processes (PHP) and two-layer ReLU neural networks. We show that the PHP with a Gaussian prior is an alternative probabilistic representation to a two-layer ReLU neural network. In addition, we show that a two-layer neural network constructed by PHP is scalable to large-scale problems via the decomposition propositions. Finally, we propose an annealed sequential Monte Carlo algorithm for Bayesian inference. Our numerical experiments demonstrate that our proposed method outperforms the classic two-layer ReLU neural network. The implementation of our proposed model is available at https://github.com/ShufeiGe/Pois_Relu.git.",
    "arxiv_id": "2601.05586",
    "authors": [
      "Shufei Ge",
      "Shijia Wang",
      "Lloyd Elliott"
    ],
    "categories": [
      "cs.LG",
      "stat.ME",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "title": "Poisson Hyperplane Processes with Rectified Linear Units",
    "url": "https://arxiv.org/abs/2601.05586",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "946fe0e7-f203-429b-b0bb-4f8b60a74d1c",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}