Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning

• URL: http://arxiv.org/abs/2606.14970v1
• Date: Fri, 12 Jun 2026 21:46:54 GMT
• Title: Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning
• Abstract summary: A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation.<n>$texttAdaNAGED$ is a method that unifies gradient-free training, adaptive tuning, and non-Euclidean update geometry.
• Score: 46.539149169728624
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse downstream tasks and domain-specific data. A major obstacle in large-scale fine-tuning is the memory overhead of backpropagation, which requires storing activations, gradients, and optimizer states. Zeroth-order (ZO) optimization offers a memory-efficient alternative, but its performance is highly sensitive to the stepsize and smoothing parameter, often requiring costly task-specific tuning. Parameter-free (PF) optimization addresses this issue by adapting algorithmic parameters without prior knowledge of problem-dependent constants. Moreover, large-scale fine-tuning can benefit from geometry-aware updates that account for the heterogeneous structure of parameter blocks, which can be modeled through methods that exploit linear minimization oracle (LMO). In this work, we study PF adaptation for LMO-based ZO optimization and introduce $\texttt{AdaNAGED}$, a method that unifies gradient-free training, adaptive tuning, and non-Euclidean update geometry. We establish convergence guarantees and validate the method on large-scale LLM fine-tuning task with $\texttt{OPT}-1.3\mathrm{B}$ model.

Related papers

• Schattor: Schatten-family methods for deep learning optimization [13.92796349861358]
  We propose a family of adaptive firstorder methods based on Schatten norms.<n>We establish dimension-free station guarantees for methods Schattor and SGD.<n>We also develop multiblock extensions that adaptively balance block-wise optimization progress.
  arXiv  Detail & Related papers  (2026-06-14T09:31:59Z)
• From SGD to Muon: Adaptive Optimization via Schatten-p Norms [3.5975968496682484]
  Moderns like Muon impose matrix-wise geometry constraints on their updates.<n>All current methods impose fixed LMO geometries for the update rules, chosen by-design or empirically, which are not optimal according to the problem's geometry.<n>We introduce a novel efficient datadriven criterion for dynamically choosing proxy-optimal update LMO geometries.
  arXiv  Detail & Related papers  (2026-05-19T12:47:41Z)
• New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework [52.69678300445233]
  Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or.<n>Efficient Fine-Tuning (PEFT) adjusts a small subset of parameters.<n>We propose a novel hybrid fine-tuning approach that jointly updates both LLMs and PEFT modules using a combination of zeroth-order and first-order optimization methods.
  arXiv  Detail & Related papers  (2026-04-10T22:39:38Z)
• Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes [3.246129789918632]
  The training of deep neural networks is inherently a non- optimization problem.<n>Standard approaches such as gradient descent (SGD) require simultaneous updates to parameters.<n>We propose a novel method Alternating Train Miniization with tailored step sizes (SAMT)<n>SAMT achieves better performance with fewer parameter updates compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-06T08:23:38Z)
• ESSA: Evolutionary Strategies for Scalable Alignment [8.418036456622158]
  We present ESSA, a gradient-free framework that aligns Large Language Models (LLMs) using only forward inference and black-box optimization.<n>ESSA improves the test accuracy of Qwen2.5-Math-7B by 12.6% on GSM8K and 14.8% on PRM800K, and raises the accuracy of LLaMA3.1-8B on IFEval by 22.5%.<n>In large-scale settings ESSA shows stronger scaling than gradient-based methods.
  arXiv  Detail & Related papers  (2025-07-06T16:23:07Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We propose a new family of algorithms that uses the linear minimization oracle (LMO) to adapt to the geometry of the problem.<n>We demonstrate significant speedups on nanoGPT training using our algorithm, Scion, without any reliance on Adam.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• Sparse Gradient Compression for Fine-Tuning Large Language Models [58.44973963468691]
  Fine-tuning large language models (LLMs) for downstream tasks has become increasingly crucial due to their widespread use and the growing availability of open-source models.<n>High memory costs associated with fine-tuning remain a significant challenge, especially as models increase in size.<n>We propose sparse compression gradient (SGC) to address these limitations.
  arXiv  Detail & Related papers  (2025-02-01T04:18:28Z)
• Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures [21.18741772731095]
  Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values. Existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs.
  arXiv  Detail & Related papers  (2024-10-10T08:10:53Z)
• LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
  Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method.<n>We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation.<n>Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
  arXiv  Detail & Related papers  (2024-10-05T06:59:50Z)
• Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark [166.40879020706151]
  This paper proposes a shift towards BP-free, zeroth-order (ZO) optimization as a solution for reducing memory costs during fine-tuning. Unlike traditional ZO-SGD methods, our work expands the exploration to a wider array of ZO optimization techniques. Our study unveils previously overlooked optimization principles, highlighting the importance of task alignment, the role of the forward gradient method, and the balance between algorithm complexity and fine-tuning performance.
  arXiv  Detail & Related papers  (2024-02-18T14:08:48Z)
• End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty [55.04219793298687]
  The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives. It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
  arXiv  Detail & Related papers  (2024-02-12T16:33:35Z)

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.