I3S: Importance Sampling Subspace Selection for Low-Rank Optimization in LLM Pretraining

• URL: http://arxiv.org/abs/2502.05790v1
• Date: Sun, 09 Feb 2025 06:30:19 GMT
• Title: I3S: Importance Sampling Subspace Selection for Low-Rank Optimization in LLM Pretraining
• Authors: Haochen Zhang, Junze Yin, Guanchu Wang, Zirui Liu, Tianyi Zhang, Anshumali Shrivastava, Lin Yang, Vladimir Braverman,
• Abstract summary: Low-rank optimization has emerged as a promising approach to enabling memory-efficient training of large language models (LLMs) Existing low-rank optimization methods typically project gradients onto a low-rank subspace, reducing the memory cost of storing states. We propose importance sampling subspace selection (I3S) for low-rank optimization, which theoretically offers a comparable convergence rate to the dominant subspace approach.
• Score: 50.89661053183944
• License:
• Abstract: Low-rank optimization has emerged as a promising approach to enabling memory-efficient training of large language models (LLMs). Existing low-rank optimization methods typically project gradients onto a low-rank subspace, reducing the memory cost of storing optimizer states. A key challenge in these methods is identifying suitable subspaces to ensure an effective optimization trajectory. Most existing approaches select the dominant subspace to preserve gradient information, as this intuitively provides the best approximation. However, we find that in practice, the dominant subspace stops changing during pretraining, thereby constraining weight updates to similar subspaces. In this paper, we propose importance sampling subspace selection (I3S) for low-rank optimization, which theoretically offers a comparable convergence rate to the dominant subspace approach. Empirically, we demonstrate that I3S significantly outperforms previous methods in LLM pretraining tasks.

Related papers

• A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models [22.725326215887435]
  We introduce a Randomized Subspace Optimization framework for pre-training and fine-tuning Large Language Models. Our approach decomposes the high-dimensional training problem into a series of lower-dimensional subproblems. This structured reduction in dimensionality allows our method to simultaneously reduce memory usage for both activations and states.
  arXiv  Detail & Related papers  (2025-02-11T03:32:10Z)
• 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)
• Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
  offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
  arXiv  Detail & Related papers  (2024-06-12T16:58:41Z)
• An Adaptive Dimension Reduction Estimation Method for High-dimensional Bayesian Optimization [6.79843988450982]
  We propose a two-step optimization framework to extend BO to high-dimensional settings. Our algorithm offers the flexibility to operate these steps either concurrently or in sequence. Numerical experiments validate the efficacy of our method in challenging scenarios.
  arXiv  Detail & Related papers  (2024-03-08T16:21:08Z)
• 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)
• AdaLomo: Low-memory Optimization with Adaptive Learning Rate [59.64965955386855]
  We introduce low-memory optimization with adaptive learning rate (AdaLomo) for large language models. AdaLomo results on par with AdamW, while significantly reducing memory requirements, thereby lowering the hardware barrier to training large language models.
  arXiv  Detail & Related papers  (2023-10-16T09:04:28Z)
• A Particle-based Sparse Gaussian Process Optimizer [5.672919245950197]
  We present a new swarm-swarm-based framework utilizing the underlying dynamical process of descent. The biggest advantage of this approach is greater exploration around the current state before deciding descent descent.
  arXiv  Detail & Related papers  (2022-11-26T09:06:15Z)
• A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning [95.85269649177336]
  ZO optimization iteratively performs three major steps: gradient estimation, descent direction, and solution update. We demonstrate promising applications of ZO optimization, such as evaluating and generating explanations from black-box deep learning models, and efficient online sensor management.
  arXiv  Detail & Related papers  (2020-06-11T06:50:35Z)

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.