Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks

• URL: http://arxiv.org/abs/2501.09137v2
• Date: Tue, 21 Jan 2025 03:05:17 GMT
• Title: Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
• Authors: Pierfrancesco Beneventano, Blake Woodworth,
• Abstract summary: We study the gradient descent dynamics of a depth-2 linear neural network with a single input and output. We show that GD converges at an explicit linear rate to a global minimum of the training loss, even with a large stepsize.
• Score: 0.0
• License:
• Abstract: We study the gradient descent (GD) dynamics of a depth-2 linear neural network with a single input and output. We show that GD converges at an explicit linear rate to a global minimum of the training loss, even with a large stepsize -- about $2/\textrm{sharpness}$. It still converges for even larger stepsizes, but may do so very slowly. We also characterize the solution to which GD converges, which has lower norm and sharpness than the gradient flow solution. Our analysis reveals a trade off between the speed of convergence and the magnitude of implicit regularization. This sheds light on the benefits of training at the ``Edge of Stability'', which induces additional regularization by delaying convergence and may have implications for training more complex models.

Related papers

• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Implicit regularization in AI meets generalized hardness of approximation in optimization -- Sharp results for diagonal linear networks [0.0]
  We show sharp results for the implicit regularization imposed by the gradient flow of Diagonal Linear Networks. We link this to the phenomenon of phase transitions in generalized hardness of approximation. Non-sharpness of our results would imply that the GHA phenomenon would not occur for the basis pursuit optimization problem.
  arXiv  Detail & Related papers  (2023-07-13T13:27:51Z)
• Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction [49.66486092259376]
  The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift. Recent works have shown that MFLD globally minimizes an entropy-regularized convex functional in the space of measures. We provide a framework to prove a uniform-in-time propagation of chaos for MFLD that takes into account the errors due to finite-particle approximation, time-discretization, and gradient approximation.
  arXiv  Detail & Related papers  (2023-06-12T16:28:11Z)
• Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond [30.545436106324203]
  We find that when Gradient Descent is applied to neural networks, the loss almost never decreases monotonically. Instead, the loss oscillates as gradient descent converges to its ''Edge of Stability'' (EoS)
  arXiv  Detail & Related papers  (2023-05-22T14:27:27Z)
• Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data [63.34506218832164]
  In this work, we investigate the implicit bias of gradient flow and gradient descent in two-layer fully-connected neural networks with ReLU activations. For gradient flow, we leverage recent work on the implicit bias for homogeneous neural networks to show that leakyally, gradient flow produces a neural network with rank at most two. For gradient descent, provided the random variance is small enough, we show that a single step of gradient descent suffices to drastically reduce the rank of the network, and that the rank remains small throughout training.
  arXiv  Detail & Related papers  (2022-10-13T15:09:54Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)
• Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks [83.58049517083138]
  We consider a two-layer ReLU network trained via gradient descent. We show that SGD is biased towards a simple solution. We also provide empirical evidence that knots at locations distinct from the data points might occur.
  arXiv  Detail & Related papers  (2021-11-03T15:14:20Z)
• AdaLoss: A computationally-efficient and provably convergent adaptive gradient method [7.856998585396422]
  We propose a computationally-friendly learning schedule, "AnomidaLoss", which uses the information of the loss function to adjust rate numerically. We verify the scope of the numerical experiments by applications in LSTM models for text and control problems.
  arXiv  Detail & Related papers  (2021-09-17T01:45:25Z)
• Convergence of gradient descent for learning linear neural networks [2.209921757303168]
  We show that gradient descent converges to a critical point of the loss function, i.e., the square loss in this article. In the case of three or more layers we show that gradient descent converges to a global minimum on the manifold matrices of some fixed rank.
  arXiv  Detail & Related papers  (2021-08-04T13:10:30Z)
• 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)
• The Implicit Bias of Gradient Descent on Separable Data [44.98410310356165]
  We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. This can help explain the benefit of continuing to optimize the logistic or cross-entropy loss even after the training error is zero.
  arXiv  Detail & Related papers  (2017-10-27T21:47:58Z)

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.