Pith. sign in

REVIEW 6 cited by

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity

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 2406.02913 v1 pith:ZGTLBHWF submitted 2024-06-05 cs.LG cs.AI

classification cs.LGcs.AI
keywords fine-tuningparametersllmssensitivedeviceforwardfullmemory
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes. However, the application of ZO fine-tuning in memory-constrained settings such as mobile phones and laptops is still challenging since full precision forward passes are infeasible. In this study, we address this limitation by integrating sparsity and quantization into ZO fine-tuning of LLMs. Specifically, we investigate the feasibility of fine-tuning an extremely small subset of LLM parameters using ZO. This approach allows the majority of un-tuned parameters to be quantized to accommodate the constraint of limited device memory. Our findings reveal that the pre-training process can identify a set of "sensitive parameters" that can guide the ZO fine-tuning of LLMs on downstream tasks. Our results demonstrate that fine-tuning 0.1% sensitive parameters in the LLM with ZO can outperform the full ZO fine-tuning performance, while offering wall-clock time speedup. Additionally, we show that ZO fine-tuning targeting these 0.1% sensitive parameters, combined with 4 bit quantization, enables efficient ZO fine-tuning of an Llama2-7B model on a GPU device with less than 8 GiB of memory and notably reduced latency.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. On the Inherent Privacy of Zeroth Order Projected Gradient Descent

    math.OC 2025-07 conditional novelty 7.0 of 10

    Zeroth-order projected gradient descent without additive Gaussian noise is not differentially private in the worst case, and its privacy loss grows superlinearly with iterations.

  2. Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    RISE applies CountSketch to dual lexical and semantic channels derived from output-layer gradient outer products, cutting data attribution storage by up to 112x and enabling retrospective and prospective influence ana...

  3. Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation

    cs.LG 2026-04 conditional novelty 6.0 of 10

    Influence scoring can use only forward passes: CountSketch-compressed outer products of the LM-head residual and final hidden state give accurate attribution and valuation from 14M to 32B parameters.

  4. Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs

    cs.LG 2025-10 conditional novelty 6.0 of 10

    A learned per-block noise-scale generator improves zeroth-order (gradient-free) fine-tuning of LLMs and can be trained once on one task and reused elsewhere.

  5. Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    Zeroth-order optimization is underexplored rather than underpowered in deep learning, with limitations stemming from full-space designs that can be addressed via subspace, spectral, and systems-aware approaches.

  6. AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    AdaMeZO adapts Adam moment estimates to zeroth-order LLM fine-tuning without extra memory storage, outperforming MeZO with up to 70% fewer forward passes.

Pith tools