Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization

• URL: http://arxiv.org/abs/2310.12298v2
• Date: Fri, 27 Oct 2023 03:59:42 GMT
• Title: Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization
• Authors: Siddharth Singh, Zachary Sating, Abhinav Bhatele
• Abstract summary: We introduce Jorge, a second-order that promises the best of both worlds -- rapid convergence benefits of second-order methods, and high computational efficiency typical of first-order methods. We address the primary computational bottleneck of computing matrix inverses by completely eliminating them using an approximation of the preconditioner.
• Score: 2.081667369602538
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their better convergence properties compared to first-order optimizers, second-order optimizers for deep learning have been less popular due to their significant computational costs. The primary efficiency bottleneck in such optimizers is matrix inverse calculations in the preconditioning step, which are expensive to compute on GPUs. In this paper, we introduce Jorge, a second-order optimizer that promises the best of both worlds -- rapid convergence benefits of second-order methods, and high computational efficiency typical of first-order methods. We address the primary computational bottleneck of computing matrix inverses by completely eliminating them using an approximation of the preconditioner computation. This makes Jorge extremely efficient on GPUs in terms of wall-clock time. Further, we describe an approach to determine Jorge's hyperparameters directly from a well-tuned SGD baseline, thereby significantly minimizing tuning efforts. Our empirical evaluations demonstrate the distinct advantages of using Jorge, outperforming state-of-the-art optimizers such as SGD, AdamW, and Shampoo across multiple deep learning models, both in terms of sample efficiency and wall-clock time.

Related papers

• SGD with Partial Hessian for Deep Neural Networks Optimization [18.78728272603732]
  We propose a compound, which is a combination of a second-order with a precise partial Hessian matrix for updating channel-wise parameters and the first-order gradient descent (SGD) algorithms for updating the other parameters. Compared with first-orders, it adopts a certain amount of information from the Hessian matrix to assist optimization, while compared with the existing second-order generalizations, it keeps the good performance of first-order generalizations imprecise.
  arXiv  Detail & Related papers  (2024-03-05T06:10:21Z)
• Eva: A General Vectorized Approximation Framework for Second-order Optimization [16.647611352181574]
  We present a memory- and time-efficient second-order algorithm named Eva with two novel techniques. We derive an efficient update formula without explicitly computing the inverse of using the Sherman-Morrison formula. Experiments show that Eva reduces the end-to-end training time up to 2.05x and 2.42x compared to first-order SGD and second-order algorithms.
  arXiv  Detail & Related papers  (2023-08-04T03:51:38Z)
• Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates [49.84541884653309]
  A current standard approach to solving convex discrete optimization problems is the use of cutting-plane algorithms. Despite the existence of a number of general-purpose cut-generating algorithms, large-scale discrete optimization problems continue to suffer from intractability. We propose a method for accelerating cutting-plane algorithms via reinforcement learning.
  arXiv  Detail & Related papers  (2023-07-17T20:11:56Z)
• Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods [75.34939761152587]
  Efficient computation of the optimal transport distance between two distributions serves as an algorithm that empowers various applications. This paper develops a scalable first-order optimization-based method that computes optimal transport to within $varepsilon$ additive accuracy.
  arXiv  Detail & Related papers  (2023-01-30T15:46:39Z)
• Learning to Optimize Quasi-Newton Methods [22.504971951262004]
  This paper introduces a novel machine learning called LODO, which tries to online meta-learn the best preconditioner during optimization. Unlike other L2O methods, LODO does not require any meta-training on a training task distribution. We show that our gradient approximates the inverse Hessian in noisy loss landscapes and is capable of representing a wide range of inverse Hessians.
  arXiv  Detail & Related papers  (2022-10-11T03:47:14Z)
• Recommender System Expedited Quantum Control Optimization [0.0]
  Quantum control optimization algorithms are routinely used to generate optimal quantum gates or efficient quantum state transfers. There are two main challenges in designing efficient optimization algorithms, namely overcoming the sensitivity to local optima and improving the computational speed. Here, we propose and demonstrate the use of a machine learning method, specifically the recommender system (RS), to deal with the latter challenge.
  arXiv  Detail & Related papers  (2022-01-29T10:25:41Z)
• Implementation of Parallel Simplified Swarm Optimization in CUDA [2.322689362836168]
  In optimization computing, intelligent swarm algorithms (SIAs) method is suitable for parallelization. This paper proposed a GPU-based Simplified Swarm Algorithm Optimization (PSSO) based on the platform considering computational ability and versatility. As the results showed, the time complexity has successfully reduced by an order of magnitude of N, and the problem of resource preemption was avoided entirely.
  arXiv  Detail & Related papers  (2021-10-01T00:15:45Z)
• 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)
• Bilevel Optimization: Convergence Analysis and Enhanced Design [63.64636047748605]
  Bilevel optimization is a tool for many machine learning problems. We propose a novel stoc-efficientgradient estimator named stoc-BiO.
  arXiv  Detail & Related papers  (2020-10-15T18:09:48Z)
• Kernel methods through the roof: handling billions of points efficiently [94.31450736250918]
  Kernel methods provide an elegant and principled approach to nonparametric learning, but so far could hardly be used in large scale problems. Recent advances have shown the benefits of a number of algorithmic ideas, for example combining optimization, numerical linear algebra and random projections. Here, we push these efforts further to develop and test a solver that takes full advantage of GPU hardware.
  arXiv  Detail & Related papers  (2020-06-18T08:16:25Z)
• Private Stochastic Convex Optimization: Optimal Rates in Linear Time [74.47681868973598]
  We study the problem of minimizing the population loss given i.i.d. samples from a distribution over convex loss functions. A recent work of Bassily et al. has established the optimal bound on the excess population loss achievable given $n$ samples. We describe two new techniques for deriving convex optimization algorithms both achieving the optimal bound on excess loss and using $O(minn, n2/d)$ gradient computations.
  arXiv  Detail & Related papers  (2020-05-10T19:52:03Z)

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.