Directional Smoothness and Gradient Methods: Convergence and Adaptivity

• URL: http://arxiv.org/abs/2403.04081v1
• Date: Wed, 6 Mar 2024 22:24:05 GMT
• Title: Directional Smoothness and Gradient Methods: Convergence and Adaptivity
• Authors: Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, and Robert M. Gower
• Abstract summary: We develop new sub-optimality bounds for gradient descent that depend on the conditioning of the objective along the path of optimization. Key to our proofs is directional smoothness, a measure of gradient variation that we use to develop upper-bounds on the objective. We prove that the Polyak step-size and normalized GD obtain fast, path-dependent rates despite using no knowledge of the directional smoothness.
• Score: 16.779513676120096
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization, rather than on global, worst-case constants. Key to our proofs is directional smoothness, a measure of gradient variation that we use to develop upper-bounds on the objective. Minimizing these upper-bounds requires solving implicit equations to obtain a sequence of strongly adapted step-sizes; we show that these equations are straightforward to solve for convex quadratics and lead to new guarantees for two classical step-sizes. For general functions, we prove that the Polyak step-size and normalized GD obtain fast, path-dependent rates despite using no knowledge of the directional smoothness. Experiments on logistic regression show our convergence guarantees are tighter than the classical theory based on L-smoothness.

Related papers

• Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity [50.25258834153574]
  We focus on the class of (strongly) convex $(L0)$-smooth functions and derive new convergence guarantees for several existing methods. In particular, we derive improved convergence rates for Gradient Descent with smoothnessed Gradient Clipping and for Gradient Descent with Polyak Stepsizes.
  arXiv  Detail & Related papers  (2024-09-23T13:11:37Z)
• Gradient-Variation Online Learning under Generalized Smoothness [56.38427425920781]
  gradient-variation online learning aims to achieve regret guarantees that scale with variations in gradients of online functions. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. We provide the applications for fast-rate convergence in games and extended adversarial optimization.
  arXiv  Detail & Related papers  (2024-08-17T02:22:08Z)
• Convergence Analysis of Adaptive Gradient Methods under Refined Smoothness and Noise Assumptions [18.47705532817026]
  We show that AdaGrad outperforms SGD by a factor of $d$ under certain conditions. Motivated by this, we introduce assumptions on the smoothness structure of the objective and the gradient variance.
  arXiv  Detail & Related papers  (2024-06-07T02:55:57Z)
• Non-Uniform Smoothness for Gradient Descent [5.64297382055816]
  We introduce a local first-order smoothness oracle (LFSO) which generalizes the Lipschitz continuous gradient smoothness condition. We show that this oracle can encode all relevant problem information for tuning stepsizes for a suitably modified gradient descent method. We also show that LFSOs in this modified first-order method can yield global linear convergence rates for non-strongly convex problems with extremely flat minima.
  arXiv  Detail & Related papers  (2023-11-15T00:44:08Z)
• Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching [55.28394191394675]
  We develop an adaptive inexact Newton method for equality-constrained nonlinear, nonIBS optimization problems. We demonstrate the superior performance of our method on benchmark nonlinear problems, constrained logistic regression with data from LVM, and a PDE-constrained problem.
  arXiv  Detail & Related papers  (2023-05-28T06:33:37Z)
• Proximal Subgradient Norm Minimization of ISTA and FISTA [8.261388753972234]
  We show that the squared proximal subgradient norm for the class of iterative shrinkage-thresholding algorithms converges at an inverse square rate. We also show that the squared proximal subgradient norm for the class of faster iterative shrinkage-thresholding algorithms (FISTA) is accelerated to convergence at an inverse cubic rate.
  arXiv  Detail & Related papers  (2022-11-03T06:50:19Z)
• Formal guarantees for heuristic optimization algorithms used in machine learning [6.978625807687497]
  Gradient Descent (SGD) and its variants have become the dominant methods in the large-scale optimization machine learning (ML) problems. We provide formal guarantees of a few convex optimization methods and proposing improved algorithms.
  arXiv  Detail & Related papers  (2022-07-31T19:41:22Z)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization [50.83356836818667]
  gradient Langevin Dynamics is one of the most fundamental algorithms to solve non-eps optimization problems. In this paper, we show two variants of this kind, namely the Variance Reduced Langevin Dynamics and the Recursive Gradient Langevin Dynamics.
  arXiv  Detail & Related papers  (2022-03-30T11:39:00Z)
• The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance [46.15915820243487]
  We show that AdaGrad-Norm exhibits an order optimal convergence of $mathcalOleft. We show that AdaGrad-Norm exhibits an order optimal convergence of $mathcalOleft.
  arXiv  Detail & Related papers  (2022-02-11T17:37:54Z)
• Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problems [120.21685755278509]
  In this work, we seek to balance the fact that attenuating step-size is required for exact convergence with the fact that constant step-size learns faster in time up to an error. Rather than fixing the minibatch the step-size at the outset, we propose to allow parameters to evolve adaptively.
  arXiv  Detail & Related papers  (2020-07-02T16:02:02Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)

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.