English
Related papers

Related papers: Lookaround Optimizer: $k$ steps around, 1 step ave…

200 papers

We present an active-set method for minimizing an objective that is the sum of a convex quadratic and $\ell_1$ regularization term. Unlike two-phase methods that combine a first-order active set identification step and a subspace phase…

Optimization and Control · Mathematics 2014-12-08 Stefan Solntsev , Jorge Nocedal , Richard Byrd

In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentum, Adam) for a variety of vision problems (classification,…

Machine Learning · Computer Science 2020-03-23 Samarth Tripathi , Jiayi Liu , Unmesh Kurup , Mohak Shah , Sauptik Dhar

Neural networks enjoy widespread use, but many aspects of their training, representation, and operation are poorly understood. In particular, our view into the training process is limited, with a single scalar loss being the most common…

Machine Learning · Computer Science 2020-03-04 Janice Lan , Rosanne Liu , Hattie Zhou , Jason Yosinski

Improving the generalization ability of modern deep neural networks (DNNs) is a fundamental challenge in machine learning. Two branches of methods have been proposed to seek flat minima and improve generalization: one led by sharpness-aware…

Machine Learning · Computer Science 2024-04-02 Tao Li , Qinghua Tao , Weihao Yan , Zehao Lei , Yingwen Wu , Kun Fang , Mingzhen He , Xiaolin Huang

Online learning updates models incrementally with new data, avoiding large storage requirements and costly model recalculations. In this paper, we introduce "OLR-WA; OnLine Regression with Weighted Average", a novel and versatile…

Machine Learning · Computer Science 2025-12-18 Mohammad Abu-Shaira , Alejandro Rodriguez , Greg Speegle , Victor Sheng , Ishfaq Ahmad

Weight decay is one of the standard tricks in the neural network toolbox, but the reasons for its regularization effect are poorly understood, and recent results have cast doubt on the traditional interpretation in terms of $L_2$…

Machine Learning · Computer Science 2018-10-30 Guodong Zhang , Chaoqi Wang , Bowen Xu , Roger Grosse

Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Hang Xu , Wei Yu , Jiangtong Tan , Zhen Zou , Feng Zhao

We address rotation averaging (RA) and its application to real-world 3D reconstruction. Local optimisation based approaches are the de facto choice, though they only guarantee a local optimum. Global optimisers ensure global optimality in…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Yu Chen , Ji Zhao , Laurent Kneip

Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor for a given…

Computer Vision and Pattern Recognition · Computer Science 2021-06-11 J. I. Forcen , Miguel Pagola , Edurne Barrenechea , Humberto Bustince

In this paper, we introduce weight prediction into the AdamW optimizer to boost its convergence when training the deep neural network (DNN) models. In particular, ahead of each mini-batch training, we predict the future weights according to…

Machine Learning · Computer Science 2023-08-09 Lei Guan

Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measurements. By allowing a wide range of degrees of weight-sharing…

Machine Learning · Computer Science 2022-01-19 Ekkehard Schnoor , Arash Behboodi , Holger Rauhut

If we want to train a neural network using any of the most popular optimization algorithms, we are immediately faced with a dilemma: how to set the various optimization and regularization hyperparameters? When computational resources are…

Machine Learning · Computer Science 2025-03-07 Sourabh Medapati , Priya Kasimbeg , Shankar Krishnan , Naman Agarwal , George Dahl

This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…

Machine Learning · Computer Science 2018-10-19 Amir Erfan Eshratifar , David Eigen , Massoud Pedram

Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…

Artificial Intelligence · Computer Science 2025-11-18 Yuhan Chen , Yuxuan Liu , Long Zhang , Pengzhi Gao , Jian Luan , Wei Liu

In complex systems, networks represent connectivity relationships between nodes through edges. Latent space models are crucial in analyzing network data for tasks like community detection and link prediction due to their interpretability…

Methodology · Statistics 2025-05-29 Yan Zhang , Jun Liao , Xinyan Fan , Kuangnan Fang , Yuhong Yang

The study on improving the robustness of deep neural networks against adversarial examples grows rapidly in recent years. Among them, adversarial training is the most promising one, which flattens the input loss landscape (loss change with…

Machine Learning · Computer Science 2020-10-14 Dongxian Wu , Shu-tao Xia , Yisen Wang

We tackle the problem of online optimization with a general, possibly unbounded, loss function. It is well known that when the loss is bounded, the exponentially weighted aggregation strategy (EWA) leads to a regret in $\sqrt{T}$ after $T$…

Machine Learning · Statistics 2022-01-17 Pierre Alquier

In this paper, we propose a general deep learning training framework XGrad which introduces weight prediction into the popular gradient-based optimizers to boost their convergence and generalization when training the deep neural network…

Machine Learning · Computer Science 2024-04-09 Lei Guan , Dongsheng Li , Yanqi Shi , Jian Meng

Designing neural networks typically relies on manual trial and error or a neural architecture search (NAS) followed by weight training. The former is time-consuming and labor-intensive, while the latter often discretizes architecture search…

Machine Learning · Computer Science 2025-11-19 Zitong Huang , Mansooreh Montazerin , Ajitesh Srivastava

Weight decay is a simple yet powerful regularization technique that has been very widely used in training of deep neural networks (DNNs). While weight decay has attracted much attention, previous studies fail to discover some overlooked…

Machine Learning · Computer Science 2024-08-19 Zeke Xie , Zhiqiang Xu , Jingzhao Zhang , Issei Sato , Masashi Sugiyama