Pith. sign in

REVIEW 3 cited by

Scaling Laws for Differentially Private Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.18914 v1 pith:6LNEJMZS submitted 2025-01-31 cs.LG cs.CR

Scaling Laws for Differentially Private Language Models

classification cs.LG cs.CR
keywords traininglawsscalingdataimportantlanguagelargelike
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs also rely on large, high-quality training datasets, like those sourced from (sometimes sensitive) user data. Training models on this sensitive user data requires careful privacy protections like differential privacy (DP). However, the dynamics of DP training are significantly different, and consequently their scaling laws are not yet fully understood. In this work, we establish scaling laws that accurately model the intricacies of DP LLM training, providing a complete picture of the compute-privacy-utility tradeoffs and the optimal training configurations in many settings.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?

    cs.LG 2026-05 unverdicted novelty 7.0

    Balanced Iteration Subsampling achieves stronger privacy amplification than Poisson subsampling in DP-SGD by eliminating participation variance while keeping uniform marginal participation.

  2. High-Dimensional Private Linear Regression with Optimal Rates

    stat.ML 2025-05 accept novelty 7.0

    DP-GD achieves minimax optimal non-asymptotic risk O(γ + γ²/ρ²) for well-conditioned high-dimensional data and power-law scaling for ill-conditioned power-law spectra, with the exponent depending on the privacy parameter ρ.

  3. Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD

    cs.LG 2026-01 unverdicted novelty 6.0

    Shuffled DP-SGD requires σ ≥ 1/√(2 ln M) or κ ≥ (1/√8)(1 - 1/√(4π ln M)) to limit adversarial advantage, preventing strong privacy and high utility simultaneously.