中文
相关论文

相关论文: Exponential Convergence Time of Gradient Descent f…

200 篇论文

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

机器学习 · 计算机科学 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

机器学习 · 计算机科学 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

机器学习 · 计算机科学 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

机器学习 · 统计学 2018-06-15 Atsushi Nitanda , Taiji Suzuki

We show that running gradient descent with variable learning rate guarantees loss $f(x) \leq 1.1 \cdot f(x^*) + \epsilon$ for the logistic regression objective, where the error $\epsilon$ decays exponentially with the number of iterations…

机器学习 · 计算机科学 2023-06-27 Kyriakos Axiotis , Maxim Sviridenko

We give a simple proof for the global convergence of gradient descent in training deep ReLU networks with the standard square loss, and show some of its improvements over the state-of-the-art. In particular, while prior works require all…

机器学习 · 计算机科学 2021-06-14 Quynh Nguyen

A vast literature on convergence guarantees for gradient descent and derived methods exists at the moment. However, a simple practical situation remains unexplored: when a fixed step size is used, can we expect gradient descent to converge…

机器学习 · 计算机科学 2024-12-10 Alexandru Crăciun , Debarghya Ghoshdastidar

We study the complexity of training neural network models with one hidden nonlinear activation layer and an output weighted sum layer. We analyze Gradient Descent applied to learning a bounded target function on $n$ real-valued inputs. We…

机器学习 · 计算机科学 2019-05-28 Santosh Vempala , John Wilmes

The proximal inertial gradient descent is efficient for the composite minimization and applicable for broad of machine learning problems. In this paper, we revisit the computational complexity of this algorithm and present other novel…

最优化与控制 · 数学 2019-07-19 Tao Sun , Linbo Qiao , Dongsheng Li

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing…

最优化与控制 · 数学 2019-11-05 Lei Li

We prove that for analytic functions in low dimension, the convergence rate of the deep neural network approximation is exponential.

机器学习 · 计算机科学 2018-07-03 Weinan E , Qingcan Wang

The incremental gradient method is a prominent algorithm for minimizing a finite sum of smooth convex functions, used in many contexts including large-scale data processing applications and distributed optimization over networks. It is a…

最优化与控制 · 数学 2022-02-09 Mert Gürbüzbalaban , Asuman Ozdaglar , Pablo Parrilo

We study whether a depth two neural network can learn another depth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradient descent converges to the target function is equivalent to…

数据结构与算法 · 计算机科学 2018-12-06 Rina Panigrahy , Sushant Sachdeva , Qiuyi Zhang

Understanding the advantages of deep neural networks trained by gradient descent (GD) compared to shallow models remains an open theoretical challenge. In this paper, we introduce a class of target functions (single and multi-index Gaussian…

机器学习 · 统计学 2025-11-17 Yatin Dandi , Luca Pesce , Lenka Zdeborová , Florent Krzakala

Deep neural networks are highly expressive machine learning models with the ability to interpolate arbitrary datasets. Deep nets are typically optimized via first-order methods and the optimization process crucially depends on the…

机器学习 · 统计学 2019-11-12 Talha Cihad Gulcu

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

机器学习 · 计算机科学 2026-01-01 Alan Oursland

In this paper, we present some theoretical work to explain why simple gradient descent methods are so successful in solving non-convex optimization problems in learning large-scale neural networks (NN). After introducing a mathematical tool…

机器学习 · 计算机科学 2023-05-01 Hui Jiang

We study the properties of alignment, a form of implicit regularization, in linear neural networks under gradient descent. We define alignment for fully connected networks with multidimensional outputs and show that it is a natural…

机器学习 · 计算机科学 2020-06-18 Adityanarayanan Radhakrishnan , Eshaan Nichani , Daniel Bernstein , Caroline Uhler

In this paper, we propose a geometric framework to analyze the convergence properties of gradient descent trajectories in the context of linear neural networks. We translate a well-known empirical observation of linear neural nets into a…

机器学习 · 计算机科学 2023-08-02 Yacine Chitour , Zhenyu Liao , Romain Couillet

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

机器学习 · 统计学 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang
‹ 上一页 1 2 3 10 下一页 ›