English
Related papers

Related papers: Closed-Form Last Layer Optimization

200 papers

Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with…

Machine Learning · Computer Science 2024-02-07 Guangfeng Yan , Tan Li , Yuanzhang Xiao , Hanxu Hou , Linqi Song

We consider stochastic approximation for the least squares regression problem in the non-strongly convex setting. We present the first practical algorithm that achieves the optimal prediction error rates in terms of dependence on the noise…

Machine Learning · Computer Science 2022-03-04 Aditya Varre , Nicolas Flammarion

We study the convergence of gradient descent (GD) and stochastic gradient descent (SGD) for training $L$-hidden-layer linear residual networks (ResNets). We prove that for training deep residual networks with certain linear transformations…

Machine Learning · Computer Science 2020-03-03 Difan Zou , Philip M. Long , Quanquan Gu

We present and analyze a novel regularized form of the gradient clipping algorithm, proving that it converges to global minima of the loss surface of deep neural networks under the squared loss, provided that the layers are of sufficient…

Machine Learning · Computer Science 2025-04-09 Matteo Tucat , Anirbit Mukherjee , Procheta Sen , Mingfei Sun , Omar Rivasplata

Neural networks have shown significant potential in solving partial differential equations (PDEs). While deep networks are capable of approximating complex functions, direct one-shot training often faces limitations in both accuracy and…

Numerical Analysis · Mathematics 2025-03-10 Mingxing Weng , Zhiping Mao , Jie Shen

We solve a regularized weighted low-rank approximation problem by a stochastic gradient descent on a manifold. To guarantee the convergence of our stochastic gradient descent, we establish a convergence theorem on manifolds for…

Optimization and Control · Mathematics 2025-02-21 Conglong Xu , Peiqi Yang , Hao Wu

Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite their empirical success, the reasons behind Adam's superior performance over SGD remain poorly…

Machine Learning · Computer Science 2026-02-19 Akiyoshi Tomihari , Issei Sato

A common pursuit in modern statistical learning is to attain satisfactory generalization out of the source data distribution (OOD). In theory, the challenge remains unsolved even under the canonical setting of covariate shift for the linear…

Machine Learning · Statistics 2025-02-14 Yuanshi Liu , Haihan Zhang , Qian Chen , Cong Fang

We propose an online learning algorithm for a class of machine learning models under a separable stochastic approximation framework. The essence of our idea lies in the observation that certain parameters in the models are easier to…

Machine Learning · Computer Science 2023-05-23 Min Gan , Xiang-xiang Su , Guang-yong Chen , Jing Chen

Inspired by the structure of spherical harmonics, we propose the truncated kernel stochastic gradient descent (T-kernel SGD) algorithm with a least-square loss function for spherical data fitting. T-kernel SGD introduces a novel…

Machine Learning · Computer Science 2025-07-17 Jinhui Bai , Lei Shi

Finding parameters in a deep neural network (NN) that fit training data is a nonconvex optimization problem, but a basic first-order optimization method (gradient descent) finds a global optimizer with perfect fit (zero-loss) in many…

Machine Learning · Computer Science 2025-03-07 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

The last layer of neural language models (LMs) projects output features of dimension $D$ to logits in dimension $V$, the size of the vocabulary, where usually $D \ll V$. This mismatch is known to raise risks of limited expressivity in…

Computation and Language · Computer Science 2026-03-12 Nathan Godey , Yoav Artzi

In this paper, we study the implicit regularization of the gradient descent algorithm in homogeneous neural networks, including fully-connected and convolutional neural networks with ReLU or LeakyReLU activations. In particular, we study…

Machine Learning · Computer Science 2021-01-01 Kaifeng Lyu , Jian Li

In this paper, we introduce StochGradAdam, a novel optimizer designed as an extension of the Adam algorithm, incorporating stochastic gradient sampling techniques to improve computational efficiency while maintaining robust performance.…

Machine Learning · Computer Science 2025-03-19 Juyoung Yun

In distributed training of deep neural networks, people usually run Stochastic Gradient Descent (SGD) or its variants on each machine and communicate with other machines periodically. However, SGD might converge slowly in training some deep…

Machine Learning · Computer Science 2022-10-14 Mingrui Liu , Zhenxun Zhuang , Yunwei Lei , Chunyang Liao

Training neural networks requires optimizing a loss function that may be highly irregular, and in particular neither convex nor smooth. Popular training algorithms are based on stochastic gradient descent with momentum (SGDM), for which…

Machine Learning · Computer Science 2026-03-17 Qinzi Zhang , Ashok Cutkosky

Neural Collapse (NC) is a recently observed phenomenon in neural networks that characterises the solution space of the final classifier layer when trained until zero training loss. Specifically, NC suggests that the final classifier layer…

Machine Learning · Computer Science 2024-11-05 Evan Markou , Thalaiyasingam Ajanthan , Stephen Gould

We introduce a new technique for gradient normalization during neural network training. The gradients are rescaled during the backward pass using normalization layers introduced at certain points within the network architecture. These…

Machine Learning · Computer Science 2021-06-18 Alejandro Cabana , Luis F. Lago-Fernández

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of…

Machine Learning · Computer Science 2023-05-23 Peter Súkeník , Marco Mondelli , Christoph Lampert

Stochastic gradient descent (SGD) is a simple and popular method to solve stochastic optimization problems which arise in machine learning. For strongly convex problems, its convergence rate was known to be O(\log(T)/T), by running SGD for…

Machine Learning · Computer Science 2015-03-19 Alexander Rakhlin , Ohad Shamir , Karthik Sridharan