Pith. sign in

REVIEW 4 cited by

AdaCliP: Adaptive Clipping for Private SGD

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1908.07643 v2 pith:ARKW4MTF submitted 2019-08-20 cs.LG cs.CRstat.ML

Venkatadheeraj Pichapati , Ananda Theertha Suresh , Felix X. Yu , Sashank J. Reddi , Sanjiv Kumar This is my paper
classification cs.LGcs.CRstat.ML
keywords adaclipalgorithmslearningmodelsnoiseprivateadaptiveclipping
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic gradient descent (SGD) algorithms for training machine learning models have been proposed. At each step, these algorithms modify the gradients and add noise proportional to the sensitivity of the modified gradients. Under this framework, we propose AdaCliP, a theoretically motivated differentially private SGD algorithm that provably adds less noise compared to the previous methods, by using coordinate-wise adaptive clipping of the gradient. We empirically demonstrate that AdaCliP reduces the amount of added noise and produces models with better accuracy.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. StraightDP: Geometry-Aware Differential Privacy for Rectified-Flow Transformers

    cs.LG 2026-07 conditional novelty 6.0 of 10

    StraightDP releases a few DP class-conditioned moments to define the noise-end velocity of a rectified flow, then uses DP-SGD only on the sample-specific part, improving strong-privacy generation accuracy.

  2. Private training in quantum machine learning

    quant-ph 2026-06 unverdicted novelty 6.0 of 10

    Hybrid QML models trained with classical DP-SGD retain higher accuracy than classical models under fixed privacy budgets on synthetic and image-classification tasks.

  3. Efficient Differentially Private Fine-Tuning of LLMs via Reinforcement Learning

    cs.LG 2025-07 reject novelty 6.0 of 10

    RLDP uses a soft actor-critic policy to adapt per-adapter clipping and noise during DP-SGD fine-tuning of LLMs, claiming utility gains and faster convergence, but the privacy proof is internally inconsistent.

  4. AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks

    cs.LG 2025-07 reject novelty 4.0 of 10

    A DP-SGD variant using top-60% gradient sparsification and coordinate-wise adaptive clipping is proposed; its privacy guarantee is not established for the actual algorithm because the mask comes from private data.

Pith tools