A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimiax Optimization

• URL: http://arxiv.org/abs/2404.12312v2
• Date: Sun, 26 May 2024 01:22:12 GMT
• Title: A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimiax Optimization
• Authors: Yuchen Zhu, Yufeng Zhang, Zhaoran Wang, Zhuoran Yang, Xiaohong Chen,
• Abstract summary: This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
• Score: 90.87444114491116
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparameterized two-layer neural networks. In particular, we consider the minimax optimization problem stemming from estimating linear functional equations defined by conditional expectations, where the objective functions are quadratic in the functional spaces. We address (i) the convergence of the stochastic gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. We establish convergence under the mean-field regime by considering the continuous-time and infinite-width limit of the optimization dynamics. Under this regime, the stochastic gradient descent-ascent corresponds to a Wasserstein gradient flow over the space of probability measures defined over the space of neural network parameters. We prove that the Wasserstein gradient flow converges globally to a stationary point of the minimax objective at a $O(T^{-1} + \alpha^{-1})$ sublinear rate, and additionally finds the solution to the functional equation when the regularizer of the minimax objective is strongly convex. Here $T$ denotes the time and $\alpha$ is a scaling parameter of the neural networks. In terms of representation learning, our results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(\alpha^{-1})$, measured in terms of the Wasserstein distance. Finally, we apply our general results to concrete examples including policy evaluation, nonparametric instrumental variable regression, asset pricing, and adversarial Riesz representer estimation.

Related papers

• Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization [7.977229957867868]
  Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L$ risk are universally consistent. In this paper, we show that the regularization term is not necessary to obtain similar results.
  arXiv  Detail & Related papers  (2023-11-24T17:04:21Z)
• Approximation Results for Gradient Descent trained Neural Networks [0.0]
  The networks are fully connected constant depth increasing width. The continuous kernel error norm implies an approximation under the natural smoothness assumption required for smooth functions.
  arXiv  Detail & Related papers  (2023-09-09T18:47:55Z)
• Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency [53.90687548731265]
  We study optimal procedures for estimating a linear functional based on observational data. For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
  arXiv  Detail & Related papers  (2023-01-16T02:57:37Z)
• 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)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function [3.5044892799305956]
  We provide a non-asymptotic analysis for the tamed un-adjusted Langevin algorithm (TUSLA) introduced in Lovas et al. In particular, we establish non-asymptotic error bounds for the TUSLA algorithm in Wassersteinstein-1-2. We show that the TUSLA algorithm converges rapidly to the optimal solution.
  arXiv  Detail & Related papers  (2021-07-19T07:13:02Z)
• q-RBFNN:A Quantum Calculus-based RBF Neural Network [31.14412266444568]
  A gradient descent based learning approach for the radial basis function neural networks (RBFNN) is proposed. The proposed method is based on the q-gradient which is also known as Jackson derivative. The proposed $q$-RBFNN is analyzed for its convergence performance in the context of least square algorithm.
  arXiv  Detail & Related papers  (2021-06-02T08:27:12Z)
• Overparameterization of deep ResNet: zero loss and mean-field analysis [19.45069138853531]
  Finding parameters in a deep neural network (NN) that fit data is a non optimization problem. We show that a basic first-order optimization method (gradient descent) finds a global solution with perfect fit in many practical situations. We give estimates of the depth and width needed to reduce the loss below a given threshold, with high probability.
  arXiv  Detail & Related papers  (2021-05-30T02:46:09Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime [50.510421854168065]
  We show that the averaged gradient descent can achieve the minimax optimal convergence rate. We show that the target function specified by the NTK of a ReLU network can be learned at the optimal convergence rate.
  arXiv  Detail & Related papers  (2020-06-22T14:31:37Z)

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.