LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM

• URL: http://arxiv.org/abs/2502.19571v1
• Date: Wed, 26 Feb 2025 21:30:34 GMT
• Title: LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM
• Authors: Yehonathan Refael, Iftach Arbel, Ofir Lindenbaum, Tom Tirer,
• Abstract summary: We study robust parameter-efficient fine-tuning (PEFT) techniques for large-language models (LLMs)<n>We present a new highly computationally efficient framework called AdaZo-SAM, combining Adam and Sharpness-Aware Minimization (SAM)<n>We also design a low-rank gradient optimization method named LORENZA, which is a memory-efficient version of AdaZo-SAM.
• Score: 13.180761892449736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study robust parameter-efficient fine-tuning (PEFT) techniques designed to improve accuracy and generalization while operating within strict computational and memory hardware constraints, specifically focusing on large-language models (LLMs). Existing PEFT methods often lack robustness and fail to generalize effectively across diverse tasks, leading to suboptimal performance in real-world scenarios. To address this, we present a new highly computationally efficient framework called AdaZo-SAM, combining Adam and Sharpness-Aware Minimization (SAM) while requiring only a single-gradient computation in every iteration. This is achieved using a stochastic zeroth-order estimation to find SAM's ascent perturbation. We provide a convergence guarantee for AdaZo-SAM and show that it improves the generalization ability of state-of-the-art PEFT methods. Additionally, we design a low-rank gradient optimization method named LORENZA, which is a memory-efficient version of AdaZo-SAM. LORENZA utilizes a randomized SVD scheme to efficiently compute the subspace projection matrix and apply optimization steps onto the selected subspace. This technique enables full-parameter fine-tuning with adaptive low-rank gradient updates, achieving the same reduced memory consumption as gradient-low-rank-projection methods. We provide a convergence analysis of LORENZA and demonstrate its merits for pre-training and fine-tuning LLMs.

Related papers

• Gradient Multi-Normalization for Stateless and Scalable LLM Training [16.037614012166063]
  Training large language models (LLMs) typically relies on adaptives like Adam which store additional state information to accelerate convergence but incur significant memory overhead.<n>Recent efforts, such as SWAN (Ma et al., 2024) address this by eliminating the need for states while achieving performance comparable to Adam via a multi-step preprocessing procedure applied to instantaneous gradients.<n>We introduce a novel framework for designing stateless gradients that normalizes gradients according to multiple norms. Experiments on pre-training LLaMA models with up to 1 billion parameters demonstrate a 3X speedup over Adam with significantly reduced memory requirements, outperforming other memory-efficient baseline
  arXiv  Detail & Related papers  (2025-02-10T18:09:53Z)
• Avoiding spurious sharpness minimization broadens applicability of SAM [13.21265875272573]
  Curvature regularization techniques like Sharpness Aware Minimization (SAM) have shown great promise in improving generalization on vision tasks. We find that SAM performs poorly in domains like natural language processing (NLP), often degrading performance -- even with twice the compute budget. We develop an alternative algorithm we call Functional-SAM, which regularizes curvature only through modification of the statistics of the overall function.
  arXiv  Detail & Related papers  (2025-02-04T15:25:47Z)
• Zeroth-Order Fine-Tuning of LLMs in Random Subspaces [66.27334633749734]
  As language models grow in size, memory demands for backpropagation increase. Zeroth-order (ZOZO) optimization methods offer a memory-efficient alternative. We show that SubZero enhances fine-tuning and achieves faster results compared to standard ZOZO approaches.
  arXiv  Detail & Related papers  (2024-10-11T17:01:43Z)
• 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)
• Flat-LoRA: Low-Rank Adaption over a Flat Loss Landscape [52.98187034726091]
  Low-Rank Adaptation (LoRA) is an efficient way to fine-tune models by optimizing only a low-rank matrix. A solution that appears flat in the LoRA space may exist sharp directions in the full parameter space, potentially harming generalization performance. We propose Flat-LoRA, an efficient approach that seeks a low-rank adaptation located in a flat region of the full parameter space.
  arXiv  Detail & Related papers  (2024-09-22T11:24:10Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• 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)
• Momentum-SAM: Sharpness Aware Minimization without Computational Overhead [0.6577148087211809]
  We propose Momentum-SAM, which perturbs parameters in the direction of the accumulated momentum vector to achieve low sharpness without significant computational overhead or memory demands. We evaluate MSAM in detail and reveal insights on separable mechanisms of NAG, SAM and MSAM regarding training optimization and generalization.
  arXiv  Detail & Related papers  (2024-01-22T15:19:18Z)
• Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer [158.2634766682187]
  Deep neural networks often suffer from poor generalization due to complex and non- unstructured loss landscapes. SharpnessAware Minimization (SAM) is a popular solution that smooths the loss by minimizing the change of landscape when adding a perturbation. In this paper, we propose Sparse SAM (SSAM), an efficient and effective training scheme that achieves perturbation by a binary mask.
  arXiv  Detail & Related papers  (2023-06-30T09:33:41Z)
• Randomized Sharpness-Aware Training for Boosting Computational Efficiency in Deep Learning [13.937644559223548]
  We propose a simple yet efficient training scheme, called Randomized Sharpness-Aware Training (RST).s in RST would perform a Bernoulli trial at each iteration to choose randomly from base algorithms (SGD) and sharpness-aware algorithms (SAM) We show that G-RST can outperform SAM in most cases while saving 50% extra cost.
  arXiv  Detail & Related papers  (2022-03-18T13:57:17Z)
• Efficient Sharpness-aware Minimization for Improved Training of Neural Networks [146.2011175973769]
  This paper proposes Efficient Sharpness Aware Minimizer (M) which boosts SAM s efficiency at no cost to its generalization performance. M includes two novel and efficient training strategies-StochasticWeight Perturbation and Sharpness-Sensitive Data Selection. We show, via extensive experiments on the CIFAR and ImageNet datasets, that ESAM enhances the efficiency over SAM from requiring 100% extra computations to 40% vis-a-vis bases.
  arXiv  Detail & Related papers  (2021-10-07T02:20:37Z)

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.