Pith Number

pith:ZMUTFYO7

pith:2026:ZMUTFYO7PUWXPEJ27NQX4KZZGK

not attested not anchored not stored refs pending

Differentially Private Model Merging

Manzil Zaheer, Qichuan Yin, Tian Li

Post-processing existing differentially private models with random selection or linear combination produces a model meeting any target privacy level without additional training.

arxiv:2604.20985 v2 · 2026-04-22 · cs.LG · cs.AI · cs.CR · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ZMUTFYO7PUWXPEJ27NQX4KZZGK}

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

We propose two post processing techniques, namely random selection and linear combination, to output a final private model for any target privacy parameter. We provide privacy accounting of these approaches from the lens of Rényi DP and privacy loss distributions for general problems. In a case study on private mean estimation, we fully characterize the privacy/utility results and theoretically establish the superiority of linear combination over random selection.

C2weakest assumption

The existing models are trained on the same dataset with different privacy/utility tradeoffs, which is required for the post-processing techniques to correctly compose privacy guarantees without additional training.

C3one line summary

Post-processing via random selection or linear combination generates differentially private models for arbitrary privacy parameters from pre-trained models on the same dataset.

Receipt and verification

First computed	2026-05-21T01:04:25.963335Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cb2932e1df7d2d77913afb617e2b3932af8e1d74f61fe1db1c2fc95ac531ea6a

Aliases

arxiv: 2604.20985 · arxiv_version: 2604.20985v2 · doi: 10.48550/arxiv.2604.20985 · pith_short_12: ZMUTFYO7PUWX · pith_short_16: ZMUTFYO7PUWXPEJ2 · pith_short_8: ZMUTFYO7

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/ZMUTFYO7PUWXPEJ27NQX4KZZGK \
  | 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: cb2932e1df7d2d77913afb617e2b3932af8e1d74f61fe1db1c2fc95ac531ea6a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c8d3a2f58553318ba692d7f377561c860b961f49b658fda3d658dcd3ee6ca237",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CR",
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-22T18:13:37Z",
    "title_canon_sha256": "74cd4d4751e8f45791432b828fb58bc3d64057097560619189ad21ff1dfc8947"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.20985",
    "kind": "arxiv",
    "version": 2
  }
}