Pith. sign in
Pith Number

pith:BVZE2YXN

pith:2026:BVZE2YXNDHB42FBYT4Y3OREEXT
not attested not anchored not stored refs pending

Adversarial Robustness of NTK Neural Networks

Yuxuan Hou

NTK neural networks achieve the minimax optimal rate for adversarial regression in Sobolev spaces when trained with gradient flow and early stopping.

arxiv:2604.25965 v2 · 2026-04-28 · stat.ML · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{BVZE2YXNDHB42FBYT4Y3OREEXT}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

NTK neural networks, trained via gradient flow with early stopping, can achieve the minimax optimal rate for adversarial regression in Sobolev spaces.

C2weakest assumption

The derivation assumes the standard nonparametric regression model with Sobolev smoothness and that the NTK training dynamics are exactly captured by the kernel gradient flow in the infinite-width limit.

C3one line summary

NTK networks achieve minimax optimal adversarial regression rates in Sobolev spaces with early stopping, but minimum-norm interpolants are vulnerable.

Receipt and verification
First computed 2026-06-09T01:05:18.206200Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0d724d62ed19c3cd14389f31b74484bcea51fd167142374443070494fce026f9

Aliases

arxiv: 2604.25965 · arxiv_version: 2604.25965v2 · doi: 10.48550/arxiv.2604.25965 · pith_short_12: BVZE2YXNDHB4 · pith_short_16: BVZE2YXNDHB42FBY · pith_short_8: BVZE2YXN
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/BVZE2YXNDHB42FBYT4Y3OREEXT \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0d724d62ed19c3cd14389f31b74484bcea51fd167142374443070494fce026f9
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "5ce242ea5fc3205372b8a2c92350a11603b3c1e59435d8043210698f1d41f04c",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2026-04-28T04:49:31Z",
    "title_canon_sha256": "e4ea70ddfbef381a88ce2d327d0aef15c1cd9b7a2d394114de4403f486bc4e2b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.25965",
    "kind": "arxiv",
    "version": 2
  }
}