Improving Adaptive Moment Optimization via Preconditioner Diagonalization

• URL: http://arxiv.org/abs/2502.07488v1
• Date: Tue, 11 Feb 2025 11:48:04 GMT
• Title: Improving Adaptive Moment Optimization via Preconditioner Diagonalization
• Authors: Son Nguyen, Bo Liu, Lizhang Chen, Qiang Liu,
• Abstract summary: We show that our approach can substantially enhance the convergence speed of modern adaptives. For large language models like LLaMA, we can achieve a speedup of 2x compared to the baseline Adam.
• Score: 11.01832755213396
• License:
• Abstract: Modern adaptive optimization methods, such as Adam and its variants, have emerged as the most widely used tools in deep learning over recent years. These algorithms offer automatic mechanisms for dynamically adjusting the update step based on estimates of gradient statistics. Compared to traditional algorithms like Stochastic Gradient Descent, these adaptive methods are typically more robust to model scale and hyperparameter tuning. However, the gradient statistics employed by these methods often do not leverage sufficient gradient covariance information, leading to suboptimal updates in certain directions of the parameter space and potentially slower convergence. In this work, we keep track of such covariance statistics in the form of a structured preconditioner matrix. Unlike other works, our approach does not apply direct approximations to estimate this matrix. We instead implement an invertible transformation that maps the preconditioner matrix into a new space where it becomes approximately diagonal. This enables a diagonal approximation of the preconditioner matrix in the transformed space, offering several computational advantages. Empirical results show that our approach can substantially enhance the convergence speed of modern adaptive optimizers. Notably, for large language models like LLaMA, we can achieve a speedup of 2x compared to the baseline Adam. Additionally, our method can be integrated with memory-efficient optimizers like Adafactor to manage computational overhead.

Related papers

• Revisiting the Initial Steps in Adaptive Gradient Descent Optimization [6.468625143772815]
  Adaptive gradient optimization methods, such as Adam, are prevalent in training deep neural networks across diverse machine learning tasks. These methods often suffer from suboptimal generalization compared to descent gradient (SGD) and exhibit instability. We introduce simple yet effective solutions: initializing the second-order moment estimation with non-zero values.
  arXiv  Detail & Related papers  (2024-12-03T04:28:14Z)
• AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix [8.975415409709575]
  We propose a novel approach to designing the preconditioning matrix by utilizing the gradient difference between two successive steps as the diagonal elements. We evaluate AGD on public generalization of Natural Language Computer Vision (CV), and Recommendation Systems (RecSys)
  arXiv  Detail & Related papers  (2023-12-04T06:20:14Z)
• Stochastic Optimization for Non-convex Problem with Inexact Hessian Matrix, Gradient, and Function [99.31457740916815]
  Trust-region (TR) and adaptive regularization using cubics have proven to have some very appealing theoretical properties. We show that TR and ARC methods can simultaneously provide inexact computations of the Hessian, gradient, and function values.
  arXiv  Detail & Related papers  (2023-10-18T10:29:58Z)
• ELRA: Exponential learning rate adaption gradient descent optimization method [83.88591755871734]
  We present a novel, fast (exponential rate), ab initio (hyper-free) gradient based adaption. The main idea of the method is to adapt the $alpha by situational awareness. It can be applied to problems of any dimensions n and scales only linearly.
  arXiv  Detail & Related papers  (2023-09-12T14:36:13Z)
• Optimization using Parallel Gradient Evaluations on Multiple Parameters [51.64614793990665]
  We propose a first-order method for convex optimization, where gradients from multiple parameters can be used during each step of gradient descent. Our method uses gradients from multiple parameters in synergy to update these parameters together towards the optima.
  arXiv  Detail & Related papers  (2023-02-06T23:39:13Z)
• Sparse high-dimensional linear regression with a partitioned empirical Bayes ECM algorithm [62.997667081978825]
  We propose a computationally efficient and powerful Bayesian approach for sparse high-dimensional linear regression. Minimal prior assumptions on the parameters are used through the use of plug-in empirical Bayes estimates. The proposed approach is implemented in the R package probe.
  arXiv  Detail & Related papers  (2022-09-16T19:15:50Z)
• Local Quadratic Convergence of Stochastic Gradient Descent with Adaptive Step Size [29.15132344744801]
  We establish local convergence for gradient descent with adaptive step size for problems such as matrix inversion. We show that these first order optimization methods can achieve sub-linear or linear convergence.
  arXiv  Detail & Related papers  (2021-12-30T00:50:30Z)
• Bolstering Stochastic Gradient Descent with Model Building [0.0]
  gradient descent method and its variants constitute the core optimization algorithms that achieve good convergence rates. We propose an alternative approach to line search by using a new algorithm based on forward step model building. We show that the proposed algorithm achieves faster convergence and better generalization in well-known test problems.
  arXiv  Detail & Related papers  (2021-11-13T06:54:36Z)
• Reducing the Variance of Gaussian Process Hyperparameter Optimization with Preconditioning [54.01682318834995]
  Preconditioning is a highly effective step for any iterative method involving matrix-vector multiplication. We prove that preconditioning has an additional benefit that has been previously unexplored. It simultaneously can reduce variance at essentially negligible cost.
  arXiv  Detail & Related papers  (2021-07-01T06:43:11Z)
• SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models [15.541264326378366]
  In recent years, implicit deep learning has emerged as a method to increase the depth of deep neural networks. The training is performed as a bi-level problem, and its computational complexity is partially driven by the iterative inversion of a huge Jacobian matrix. We propose a novel strategy to tackle this computational bottleneck from which many bi-level problems suffer.
  arXiv  Detail & Related papers  (2021-06-01T15:07:34Z)
• Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering [53.523517926927894]
  We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics. We prove that our model-based procedure converges in noisy gradient setting. This is an interesting step for constructing self-tuning quadratics.
  arXiv  Detail & Related papers  (2020-11-09T22:07:30Z)

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.