{
  "annotation_id": "a9f37101-9ce2-462c-bf44-8ed73f7d3127",
  "date_created": "2026-02-17T05:53:04.258000Z",
  "date_modified": "2026-02-17T05:53:04.258000Z",
  "file_hash": "7d6e976a8db245781b806e304d06687f8c6be9070f0b69655c2ab872cda7743e",
  "private": false,
  "record": {
    "abstract": "Neural networks (NNs) can be viewed as approximation tools. Traditionally, NNs are relying on gradient and stochastic gradient (SG) methods. There are a number of available computational packages for constructing least squares approximations, while uniform (minimax) approximations are hard due to their nonsmooth nature. It was recently demonstrated that a difference convex (DC) programming approach is an efficient alternative optimiser for NNs. In this paper, we demonstrate that a DC programming approach is also efficient for minimax approximation. In our numerical experiments, we compare a DC-programming approach and ADAMAX, a commonly used method for minimax NN approximations.",
    "arxiv_id": "2601.05557",
    "authors": [
      "Vinesha Peiris",
      "Nadezda Sukhorukova"
    ],
    "categories": [
      "math.OC"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Difference of Convex (DC) approach for neural network approximation with uniform loss function",
    "url": "https://arxiv.org/abs/2601.05557",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "7e5174e3-7812-4cdb-88f2-5eeeb184c168",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}