{
  "annotation_id": "dae0b592-b93a-447f-9a6e-5d683f8cec63",
  "date_created": "2026-02-17T05:53:05.056000Z",
  "date_modified": "2026-02-17T05:53:05.056000Z",
  "file_hash": "4c9539f26217b87d3b8f9175093f15ad5e732ff36d22f3b2d5d35318f1267f5b",
  "private": false,
  "record": {
    "abstract": "Non-parametric distributional regression has achieved significant milestones in recent years. Among these, the Tabular Prior-Data Fitted Network (TabPFN) has demonstrated state-of-the-art performance on various benchmarks. However, a challenge remains in extending these grid-based approaches to a truly multivariate setting. In a naive non-parametric discretization with $N$ bins per dimension, the complexity of an explicit joint grid scales exponentially and the paramer count of the neural networks rise sharply. This scaling is particularly detrimental in low-data regimes, as the final projection layer would require many parameters, leading to severe overfitting and intractability.",
    "arxiv_id": "2601.05683",
    "authors": [
      "Jonas Landsgesell"
    ],
    "categories": [
      "cond-mat.soft",
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "title": "Joint Optimization of Neural Autoregressors via Scoring rules",
    "url": "https://arxiv.org/abs/2601.05683",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "2dd7fc02-8fb2-48ee-89ed-e11754efcb97",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}