English
Related papers

Related papers: 1st-Order Magic: Analysis of Sharpness-Aware Minim…

200 papers

Despite extensive studies, the underlying reason as to why overparameterized neural networks can generalize remains elusive. Existing theory shows that common stochastic optimizers prefer flatter minimizers of the training loss, and thus a…

Machine Learning · Computer Science 2023-07-25 Kaiyue Wen , Zhiyuan Li , Tengyu Ma

Segment anything model (SAM) has demonstrated excellent generalizability in common vision scenarios, yet falling short of the ability to understand specialized data. Recently, several methods have combined parameter-efficient techniques…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Yiran Song , Qianyu Zhou , Xuequan Lu , Zhiwen Shao , Lizhuang Ma

Respiratory sound classification is hindered by the limited size, high noise levels, and severe class imbalance of benchmark datasets like ICBHI 2017. While Transformer-based models offer powerful feature extraction capabilities, they are…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-30 Atakan Işık , Selin Vulga Işık , Ahmet Feridun Işık , Mahşuk Taylan

The majorization-minimization (MM) principle is an extremely general framework for deriving optimization algorithms. It includes the expectation-maximization (EM) algorithm, proximal gradient algorithm, concave-convex procedure, quadratic…

Optimization and Control · Mathematics 2021-06-08 Kenneth Lange , Joong-Ho Won , Alfonso Landeros , Hua Zhou

Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Bo Zhang , Zhuotao Tian , Xin Tao , Songlin Tang , Jun Yu , Wenjie Pei

Generally, discretization of partial differential equations (PDEs) creates a sequence of linear systems $A_k x_k = b_k, k = 0, 1, 2, ..., N$ with well-known and structured sparsity patterns. Preconditioners are often necessary to achieve…

Numerical Analysis · Mathematics 2024-06-26 Rishad Islam , Arielle Carr , Colin Jacobs

Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always yields an entirely new model for each task. Currently, many…

Computation and Language · Computer Science 2022-11-29 Zihao Fu , Haoran Yang , Anthony Man-Cho So , Wai Lam , Lidong Bing , Nigel Collier

Recent experiments have shown that, often, when training a neural network with gradient descent (GD) with a step size $\eta$, the operator norm of the Hessian of the loss grows until it approximately reaches $2/\eta$, after which it…

Machine Learning · Computer Science 2024-06-07 Philip M. Long , Peter L. Bartlett

The diverse world of machine learning applications has given rise to a plethora of algorithms and optimization methods, finely tuned to the specific regression or classification task at hand. We reduce the complexity of algorithm design for…

Optimization and Control · Mathematics 2016-05-23 Zeyuan Allen-Zhu , Elad Hazan

In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of…

Machine Learning · Computer Science 2024-10-08 Gus Kristiansen , Mark Sandler , Andrey Zhmoginov , Nolan Miller , Anirudh Goyal , Jihwan Lee , Max Vladymyrov

In this paper, we address the challenge of image resolution variation for the Segment Anything Model (SAM). SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Yiran Song , Qianyu Zhou , Xiangtai Li , Deng-Ping Fan , Xuequan Lu , Lizhuang Ma

We consider the problem of minimizing a high-dimensional objective function, which may include a regularization term, using (possibly noisy) evaluations of the function. Such optimization is also called derivative-free, zeroth-order, or…

Optimization and Control · Mathematics 2023-03-20 HanQin Cai , Daniel Mckenzie , Wotao Yin , Zhenliang Zhang

Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which…

Computer Vision and Pattern Recognition · Computer Science 2024-10-24 Yichi Zhang , Jin Yang , Yuchen Liu , Yuan Cheng , Yuan Qi

Stochastic approximation techniques play an important role in solving many problems encountered in machine learning or adaptive signal processing. In these contexts, the statistics of the data are often unknown a priori or their direct…

Optimization and Control · Mathematics 2016-09-27 Chouzenoux Emilie , Pesquet Jean-Christophe

This article aims to provide a comprehensive overview of sparse optimization, with a focus on both sparse signal recovery and sparse regularization techniques. We will begin by exploring the foundations of sparse optimization, delving into…

History and Overview · Mathematics 2026-01-13 Jun Lu

In this work, to efficiently help escape the stationary and saddle points, we propose, analyze, and generalize a stochastic strategy performed as an operator for a first-order gradient descent algorithm in order to increase the target…

Machine Learning · Computer Science 2022-05-23 Wei Zhang , Yu Bao

We present a general technique for the analysis of first-order methods. The technique relies on the construction of a duality gap for an appropriate approximation of the objective function, where the function approximation improves as the…

Optimization and Control · Mathematics 2019-12-12 Jelena Diakonikolas , Lorenzo Orecchia

Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene. This results in significant performance degradation when…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Xiaoyong Lu , Yaping Yan , Tong Wei , Songlin Du

The technique of abstracting abstract machines (AAM) provides a systematic approach for deriving computable approximations of evaluators that are easily proved sound. This article contributes a complementary step-by-step process for…

Programming Languages · Computer Science 2013-07-25 J. Ian Johnson , Nicholas Labich , Matthew Might , David Van Horn

Many high-dimensional optimisation problems exhibit rich geometric structures in their set of minimisers, often forming smooth manifolds due to over-parametrisation or symmetries. When this structure is known, at least locally, it can be…

Optimization and Control · Mathematics 2025-10-27 Evan Markou , Thalaiyasingam Ajanthan , Stephen Gould