Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling

• URL: http://arxiv.org/abs/2602.13659v1
• Date: Sat, 14 Feb 2026 08:01:41 GMT
• Title: Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
• Authors: Valery Parfenov, Grigoriy Evseev, Andrey Veprikov, Nikolay Bushkov, Stanislav Moiseev, Aleksandr Beznosikov,
• Abstract summary: We propose a policy-driven ZO framework that treats the sampling distribution over perturbation directions as a learnable policy.<n>We show that learned sampling improves quality gradient information and relax the explicit dependence on $d$ in convergence bounds.<n>Our results suggest that adaptive direction sampling is a promising route to make ZO fine-tuning viable at scale.
• Score: 40.94400211806987
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation and large optimizer States) limit deployment in resource-constrained settings. Zero-order (ZO) methods bypass backpropagation by estimating directional derivatives from forward evaluations, offering substantial memory savings. However, classical ZO estimators suffer from high variance and an adverse dependence on the parameter dimensionality $d$, which has constrained their use to low-dimensional problems. In this work, we propose a policy-driven ZO framework that treats the sampling distribution over perturbation directions as a learnable policy and updates it to reduce the variance of directional estimates. We develop a practical algorithm implementing this idea and provide a theoretical analysis, showing that learned sampling distributions improve the quality of gradient information and relax the explicit dependence on $d$ in convergence bounds. Empirically, we validate the approach on challenging LLM fine-tuning benchmarks, demonstrating substantially improved performance compared to standard ZO baselines. Our results suggest that adaptive direction sampling is a promising route to make ZO fine-tuning viable at scale. The source code is available at https://github.com/brain-lab-research/zo_ldsd

Related papers

• $\ abla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space [71.23672814629448]
  $nabla$-Reasoner is an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop.<n>$nabla$-Reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark.
  arXiv  Detail & Related papers  (2026-03-05T08:42:54Z)
• Prior-Informed Zeroth-Order Optimization with Adaptive Direction Alignment for Memory-Efficient LLM Fine-Tuning [4.278794376089146]
  We propose a plug-and-play method that incorporates prior-informed perturbations to refine gradient estimation.<n>Our method significantly accelerates convergence compared to standard ZO approaches.<n>We prove that our gradient estimator achieves stronger alignment with the true gradient direction.
  arXiv  Detail & Related papers  (2026-01-08T08:27:15Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order [39.25335214877435]
  Fine-tuning Large Language Models (LLMs) is essential for adapting pre-trained models to downstream tasks.<n>Traditional first-order algorithms incur prohibitive memory and computational costs that scale poorly with model size.<n>We propose zero-order (ZO) optimization methods as a memory- and compute-efficient alternative.
  arXiv  Detail & Related papers  (2025-06-04T20:27:17Z)
• Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning [44.907586955452295]
  Large language models (LLMs) excel across various tasks, but standard first-order (FO) fine-tuning demands considerable memory.<n>Recently, zeroth-order (ZO) optimization stood out as a promising memory-efficient training paradigm.<n>We introduce a novel layer-wise divergence analysis that uncovers the distinct update pattern of FO and ZO optimization.<n>Our results demonstrate that DiZO significantly reduces the needed iterations for convergence without sacrificing throughput.
  arXiv  Detail & Related papers  (2025-02-05T16:03:17Z)
• Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach [51.76826149868971]
  Policy evaluation via Monte Carlo simulation is at the core of many MC Reinforcement Learning (RL) algorithms. We propose as a quality index a surrogate of the mean squared error of a return estimator that uses trajectories of different lengths. We present an adaptive algorithm called Robust and Iterative Data collection strategy Optimization (RIDO)
  arXiv  Detail & Related papers  (2024-10-17T11:47:56Z)
• Zeroth-Order Fine-Tuning of LLMs in Random Subspaces [63.10833446782114]
  As language models grow in size, memory demands for backpropagation increase.<n>Zeroth-order (ZO) optimization methods offer a memory-efficient alternative.<n>In this paper, we propose Subspace Zero-order optimization to address the challenges posed by posed by high dimensionality perturbations.
  arXiv  Detail & Related papers  (2024-10-11T17:01:43Z)
• Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization [9.618391485742968]
  Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs) We present an uncertainty-enhanced textbfPreference textbfOptimization framework to make the LLM self-evolve with reliable feedback. Our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization.
  arXiv  Detail & Related papers  (2024-09-17T14:05:58Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.