English
Related papers

Related papers: Gradient Descent Happens in a Tiny Subspace

200 papers

We consider the optimization problem of minimizing the logistic loss with gradient descent to train a linear model for binary classification with separable data. With a budget of $T$ iterations, it was recently shown that an accelerated…

Machine Learning · Computer Science 2026-02-16 Michael Crawshaw , Mingrui Liu

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…

Machine Learning · Computer Science 2023-06-27 Kyriakos Axiotis , Maxim Sviridenko

In this work, we study non-asymptotic bounds on correlation between two time realizations of stable linear systems with isotropic Gaussian noise. Consequently, via sampling from a sub-trajectory and using \emph{Talagrands'} inequality, we…

Machine Learning · Statistics 2023-04-05 Muhammad Abdullah Naeem

Sign-based optimization methods have become popular in machine learning due to their favorable communication cost in distributed optimization and their surprisingly good performance in neural network training. Furthermore, they are closely…

Machine Learning · Computer Science 2020-02-20 Lukas Balles , Fabian Pedregosa , Nicolas Le Roux

The success of deep architectures is at least in part attributed to the layer-by-layer unsupervised pre-training that initializes the network. Various papers have reported extensive empirical analysis focusing on the design and…

Machine Learning · Computer Science 2015-02-13 Vamsi K Ithapu , Sathya Ravi , Vikas Singh

While stochastic gradient descent (SGD) and variants have been surprisingly successful for training deep nets, several aspects of the optimization dynamics and generalization are still not well understood. In this paper, we present new…

Machine Learning · Computer Science 2019-07-26 Xinyan Li , Qilong Gu , Yingxue Zhou , Tiancong Chen , Arindam Banerjee

A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical generalization to better…

Machine Learning · Computer Science 2019-05-27 Sathya N. Ravi , Tuan Dinh , Vishnu Lokhande , Vikas Singh

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

Machine Learning · Computer Science 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan

We analyze the properties of gradient descent on convex surrogates for the zero-one loss for the agnostic learning of linear halfspaces. If $\mathsf{OPT}$ is the best classification error achieved by a halfspace, by appealing to the notion…

Machine Learning · Computer Science 2021-02-16 Spencer Frei , Yuan Cao , Quanquan Gu

We study the connection between gradient-based meta-learning and convex op-timisation. We observe that gradient descent with momentum is a special case of meta-gradients, and building on recent results in optimisation, we prove convergence…

Machine Learning · Computer Science 2023-01-10 Sebastian Flennerhag , Tom Zahavy , Brendan O'Donoghue , Hado van Hasselt , András György , Satinder Singh

Fitting neural networks often resorts to stochastic (or similar) gradient descent which is a noise-tolerant (and efficient) resolution of a gradient descent dynamics. It outputs a sequence of networks parameters, which sequence evolves…

Machine Learning · Statistics 2021-04-15 Gabriel Turinici

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration…

Machine Learning · Computer Science 2022-07-07 Ryuichi Ito , Seng Pei Liew , Tsubasa Takahashi , Yuya Sasaki , Makoto Onizuka

Neural network training is typically viewed as gradient descent on a loss surface. We propose a fundamentally different perspective: learning is a structure-preserving transformation (a functor L) between the space of network parameters…

Machine Learning · Computer Science 2025-10-07 Abdulrahman Tamim

Deep learning neural network models must be large enough to adapt to their problem domain, while small enough to avoid overfitting training data during gradient descent. To balance these competing demands, over-provisioned deep learning…

Machine Learning · Computer Science 2025-09-04 B. N. Kausik

Recent theoretical results show that gradient descent on deep neural networks under exponential loss functions locally maximizes classification margin, which is equivalent to minimizing the norm of the weight matrices under margin…

Machine Learning · Computer Science 2021-07-22 Andrzej Banburski , Fernanda De La Torre , Nishka Pant , Ishana Shastri , Tomaso Poggio

Back-propagation is a popular machine learning algorithm that uses gradient descent in training neural networks for supervised learning, but can be very slow. A number of algorithms have been developed to speed up convergence and improve…

Neural and Evolutionary Computing · Computer Science 2020-09-29 Ho Ling Li

Stochastic gradient descent (SGD) has been found to be surprisingly effective in training a variety of deep neural networks. However, there is still a lack of understanding on how and why SGD can train these complex networks towards a…

Machine Learning · Computer Science 2019-01-03 Yi Zhou , Junjie Yang , Huishuai Zhang , Yingbin Liang , Vahid Tarokh

Modern deep networks are trained with stochastic gradient descent (SGD) whose key hyperparameters are the number of data considered at each step or batch size $B$, and the step size or learning rate $\eta$. For small $B$ and large $\eta$,…

Machine Learning · Computer Science 2024-02-29 Antonio Sclocchi , Matthieu Wyart

We prove that all 'gradient span algorithms' have asymptotically deterministic behavior on scaled Gaussian random functions as the dimension tends to infinity. In particular, this result explains the counterintuitive phenomenon that…

Machine Learning · Statistics 2024-10-15 Felix Benning , Leif Döring

Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' effect exists in which the generalization error initially…

Machine Learning · Computer Science 2021-08-30 Cory Stephenson , Tyler Lee