English
Related papers

Related papers: Optimal Rates for Averaged Stochastic Gradient Des…

200 papers

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the…

Machine Learning · Computer Science 2025-07-31 Adwait Datar , Nihat Ay

Neural networks are known for their ability to approximate smooth functions, yet they fail to generalize perfectly to unseen inputs when trained on discrete operations. Such operations lie at the heart of algorithmic tasks such as…

Machine Learning · Computer Science 2026-02-03 Artur Back de Luca , George Giapitzakis , Kimon Fountoulakis

In this paper, we study a Markov chain-based stochastic gradient algorithm in general Hilbert spaces, aiming at approximating the optimal solution of a quadratic loss function. We establish probabilistic upper bounds on its convergence. We…

Machine Learning · Statistics 2025-12-16 Priyanka Roy , Susanne Saminger-Platz

As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK…

Machine Learning · Computer Science 2022-07-18 Greg Yang , Edward J. Hu

We propose to optimize neural networks with a uniformly-distributed random learning rate. The associated stochastic gradient descent algorithm can be approximated by continuous stochastic equations and analyzed within the Fokker-Planck…

Machine Learning · Computer Science 2020-10-13 Daniele Musso

The softmax activation function plays a crucial role in the success of large language models (LLMs), particularly in the self-attention mechanism of the widely adopted Transformer architecture. However, the underlying learning dynamics that…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Empirical studies show that gradient-based methods can learn deep neural networks (DNNs) with very good generalization performance in the over-parameterization regime, where DNNs can easily fit a random labeling of the training data. Very…

Machine Learning · Computer Science 2019-11-28 Yuan Cao , Quanquan Gu

In this article, we review the literature on statistical theories of neural networks from three perspectives: approximation, training dynamics and generative models. In the first part, results on excess risks for neural networks are…

Machine Learning · Statistics 2024-09-17 Namjoon Suh , Guang Cheng

Neural tangent kernels (NTKs) are a powerful tool for analyzing deep, non-linear neural networks. In the infinite-width limit, NTKs can easily be computed for most common architectures, yielding full analytic control over the training…

Machine Learning · Computer Science 2026-02-16 Max Guillen , Philipp Misof , Jan E. Gerken

We study non-convex subgradient flows for training two-layer ReLU neural networks from a convex geometry and duality perspective. We characterize the implicit bias of unregularized non-convex gradient flow as convex regularization of an…

Machine Learning · Computer Science 2021-10-14 Yifei Wang , Mert Pilanci

The Neural Tangent Kernel (NTK) is the wide-network limit of a kernel defined using neural networks at initialization, whose embedding is the gradient of the output of the network with respect to its parameters. We study the "after kernel",…

Machine Learning · Computer Science 2021-12-14 Philip M. Long

Backpropagation with gradient descent is a common optimization strategy employed by most neural network architectures in machine learning. However, finding optimal hyperparameters to guide training has proven challenging. While it is widely…

Machine Learning · Computer Science 2026-05-20 Vy Bui , Hang Yu , Karthik Kantipudi , Ziv Yaniv , Stefan Jaeger

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection…

Machine Learning · Computer Science 2014-06-17 Francesco Orabona

Graph Neural Networks (GNNs) are powerful tools for addressing learning problems on graph structures, with a wide range of applications in molecular biology and social networks. However, the theoretical foundations underlying their…

Machine Learning · Computer Science 2025-01-27 Dhiraj Patel , Anton Savostianov , Michael T. Schaub

Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem. The key question is then under what conditions can one prove that optimization…

Machine Learning · Computer Science 2017-02-28 Alon Brutzkus , Amir Globerson

In this paper, we consider the nonparametric least square regression in a Reproducing Kernel Hilbert Space (RKHS). We propose a new randomized algorithm that has optimal generalization error bounds with respect to the square loss, closing a…

Machine Learning · Computer Science 2019-05-28 Kwang-Sung Jun , Ashok Cutkosky , Francesco Orabona

This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory. It is well known that as the network's width tends to…

Machine Learning · Statistics 2024-10-10 Guhan Chen , Yicheng Li , Qian Lin

We prove that a randomly initialized neural network of *any architecture* has its Tangent Kernel (NTK) converge to a deterministic limit, as the network widths tend to infinity. We demonstrate how to calculate this limit. In prior…

Machine Learning · Statistics 2020-12-01 Greg Yang

We study the problem of learning a low-degree spherical polynomial of degree $k_0 = \Theta(1) \ge 1$ defined on the unit sphere in $\RR^d$ by training an over-parameterized two-layer neural network with augmented feature in this paper. Our…

Machine Learning · Statistics 2026-03-24 Yingzhen Yang , Ping Li