The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms

• URL: http://arxiv.org/abs/2405.19585v2
• Date: Wed, 13 Nov 2024 21:51:46 GMT
• Title: The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms
• Authors: Elizabeth Collins-Woodfin, Inbar Seroussi, Begoña García Malaxechebarría, Andrew W. Mackenzie, Elliot Paquette, Courtney Paquette,
• Abstract summary: We develop a framework for analyzing the training and learning rate dynamics on a large class of high-dimensional optimization problems. We give exact expressions for the risk and learning rate curves in terms of a deterministic solution to a system of ODEs. We investigate in detail two adaptive learning rates -- an idealized exact line search and AdaGrad-Norm on the least squares problem.
• Score: 8.681909776958184
• License:
• Abstract: We develop a framework for analyzing the training and learning rate dynamics on a large class of high-dimensional optimization problems, which we call the high line, trained using one-pass stochastic gradient descent (SGD) with adaptive learning rates. We give exact expressions for the risk and learning rate curves in terms of a deterministic solution to a system of ODEs. We then investigate in detail two adaptive learning rates -- an idealized exact line search and AdaGrad-Norm -- on the least squares problem. When the data covariance matrix has strictly positive eigenvalues, this idealized exact line search strategy can exhibit arbitrarily slower convergence when compared to the optimal fixed learning rate with SGD. Moreover we exactly characterize the limiting learning rate (as time goes to infinity) for line search in the setting where the data covariance has only two distinct eigenvalues. For noiseless targets, we further demonstrate that the AdaGrad-Norm learning rate converges to a deterministic constant inversely proportional to the average eigenvalue of the data covariance matrix, and identify a phase transition when the covariance density of eigenvalues follows a power law distribution. We provide our code for evaluation at https://github.com/amackenzie1/highline2024.

Related papers

• 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)
• Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates [34.81849268839475]
  We study the problem of efficiently computing the derivative of the fixed-point of a parametric nondifferentiable contraction map. We analyze two popular approaches: iterative differentiation (ITD) and approximate implicit differentiation (AID) We establish rates for the convergence of NSID, encompassing the best available rates in the smooth setting.
  arXiv  Detail & Related papers  (2024-03-18T11:37:53Z)
• Improving Adaptive Online Learning Using Refined Discretization [44.646191058243645]
  We study unconstrained Online Linear Optimization with Lipschitz losses. Motivated by the pursuit of instance optimality, we propose a new algorithm. Central to these results is a continuous time approach to online learning.
  arXiv  Detail & Related papers  (2023-09-27T21:54:52Z)
• 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)
• Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions [28.30744223973527]
  We give a computationally efficient algorithm that is the first to enjoy the statistically optimal log(T/sigma) regret for realizable K-wise linear classification. We develop a novel characterization of the geometry of the disagreement region induced by generalized linear classifiers.
  arXiv  Detail & Related papers  (2022-05-25T21:31:36Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information [37.70729542263343]
  We present a novel adaptive optimization algorithm for large-scale machine learning problems. Our method dynamically adapts the direction and step-size. Our methodology does not require a tedious tuning rate tuning.
  arXiv  Detail & Related papers  (2021-09-11T06:39:50Z)
• Benign Overfitting of Constant-Stepsize SGD for Linear Regression [122.70478935214128]
  inductive biases are central in preventing overfitting empirically. This work considers this issue in arguably the most basic setting: constant-stepsize SGD for linear regression. We reflect on a number of notable differences between the algorithmic regularization afforded by (unregularized) SGD in comparison to ordinary least squares.
  arXiv  Detail & Related papers  (2021-03-23T17:15:53Z)
• Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate [105.62979485062756]
  This paper attempts to characterize the particular regularization effect of SGD in the moderate learning rate regime. We show that SGD converges along the large eigenvalue directions of the data matrix, while GD goes after the small eigenvalue directions.
  arXiv  Detail & Related papers  (2020-11-04T21:07:52Z)
• GTAdam: Gradient Tracking with Adaptive Momentum for Distributed Online Optimization [4.103281325880475]
  This paper deals with a network of computing agents aiming to solve an online optimization problem in a distributed fashion, by means of local computation and communication, without any central coordinator. We propose the gradient tracking with adaptive momentum estimation (GTAdam) distributed algorithm, which combines a gradient tracking mechanism with first and second order momentum estimates of the gradient. In these numerical experiments from multi-agent learning, GTAdam outperforms state-of-the-art distributed optimization methods.
  arXiv  Detail & Related papers  (2020-09-03T15:20:21Z)
• Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms [69.45237691598774]
  We study the problem of least squares linear regression where the data-points are dependent and are sampled from a Markov chain. We establish sharp information theoretic minimax lower bounds for this problem in terms of $tau_mathsfmix$. We propose an algorithm based on experience replay--a popular reinforcement learning technique--that achieves a significantly better error rate.
  arXiv  Detail & Related papers  (2020-06-16T04:26:50Z)

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.