English
Related papers

Related papers: Explore the Loss space with Hill-ADAM

200 papers

Sharpness-Aware Minimization (SAM) is widely used to seek flatter minima -- often linked to better generalization. In its standard implementation, SAM updates the current iterate using the loss gradient evaluated at a point perturbed by…

Machine Learning · Computer Science 2026-02-06 Chanwoong Park , Uijeong Jang , Ernest K. Ryu , Insoon Yang

Sharpness-Aware Minimization (SAM) optimizer enhances the generalization ability of the machine learning model by exploring the flat minima landscape through weight perturbations. Despite its empirical success, SAM introduces an additional…

Machine Learning · Computer Science 2025-06-02 Yifei Cheng , Li Shen , Hao Sun , Nan Yin , Xiaochun Cao , Enhong Chen

Finding lower and better-generalizing minima is crucial for deep learning. However, most existing optimizers stop searching the parameter space once they reach a local minimum. Given the complex geometric properties of the loss landscape,…

Machine Learning · Computer Science 2025-11-03 Tong Zhao , Jiacheng Li , Yuanchang Zhou , Guangming Tan , Weile Jia

Sharpness-Aware Minimization (SAM) has been demonstrated to improve the generalization performance of overparameterized models by seeking flat minima on the loss landscape through optimizing model parameters that incur the largest loss…

Machine Learning · Computer Science 2025-06-10 Tian Li , Tianyi Zhou , Jeffrey A. Bilmes

Optimization is finding the best solution, which mathematically amounts to locating the global minimum of some cost function. Optimization is traditionally automated with digital or quantum computers, each having their limitations and none…

Statistical Mechanics · Physics 2021-11-16 Natalia B. Janson , Christopher J. Marsden

We propose a new variant of the Adam optimizer called MicroAdam that specifically minimizes memory overheads, while maintaining theoretical convergence guarantees. We achieve this by compressing the gradient information before it is fed…

Machine Learning · Computer Science 2024-11-06 Ionut-Vlad Modoranu , Mher Safaryan , Grigory Malinovsky , Eldar Kurtic , Thomas Robert , Peter Richtarik , Dan Alistarh

Adaptive gradient-based optimizers, notably Adam, have left their mark in training large-scale deep learning models, offering fast convergence and robustness to hyperparameter settings. However, they often struggle with generalization,…

Averaging techniques such as Ruppert--Polyak averaging and exponential movering averaging (EMA) are powerful approaches to accelerate optimization procedures of stochastic gradient descent (SGD) optimization methods such as the popular ADAM…

Optimization and Control · Mathematics 2025-05-29 Arnulf Jentzen , Julian Kranz , Adrian Riekert

Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers. Two methods have…

Machine Learning · Computer Science 2023-01-30 Jean Kaddour , Linqing Liu , Ricardo Silva , Matt J. Kusner

Optimization of non-convex loss surfaces containing many local minima remains a critical problem in a variety of domains, including operations research, informatics, and material design. Yet, current techniques either require extremely high…

Machine Learning · Computer Science 2021-07-21 Amil Merchant , Luke Metz , Sam Schoenholz , Ekin Dogus Cubuk

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

Sharpness-Aware Minimization (SAM) improves generalization by minimizing the worst-case loss within a fixed parameter-space radius neighborhood. SAM and its variants mainly rely on a first-order linearized surrogate, while flat minima are…

Machine Learning · Computer Science 2026-05-12 Jinping Wang , Qinhan Liu , Zhiwu Xie , Zhiqiang Gao

Following the introduction of Adam, several novel adaptive optimizers for deep learning have been proposed. These optimizers typically excel in some tasks but may not outperform Adam uniformly across all tasks. In this work, we introduce…

Machine Learning · Computer Science 2024-06-18 Kaan Ozkara , Can Karakus , Parameswaran Raman , Mingyi Hong , Shoham Sabach , Branislav Kveton , Volkan Cevher

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

In today's heavily overparameterized models, the value of the training loss provides few guarantees on model generalization ability. Indeed, optimizing only the training loss value, as is commonly done, can easily lead to suboptimal model…

Machine Learning · Computer Science 2021-04-30 Pierre Foret , Ariel Kleiner , Hossein Mobahi , Behnam Neyshabur

We introduce LDAdam, a memory-efficient optimizer for training large models, that performs adaptive optimization steps within lower dimensional subspaces, while consistently exploring the full parameter space during training. This strategy…

Machine Learning · Computer Science 2025-03-04 Thomas Robert , Mher Safaryan , Ionut-Vlad Modoranu , Dan Alistarh

Despite the popularity of the Adam optimizer in practice, most theoretical analyses study Stochastic Gradient Descent (SGD) as a proxy for Adam, and little is known about how the solutions found by Adam differ. In this paper, we show that…

Machine Learning · Computer Science 2025-11-05 Xinghan Li , Haodong Wen , Kaifeng Lyu

The insufficient generalization of adaptive moment estimation (Adam) has hindered its broader application. Recent studies have shown that flat minima in loss landscapes are highly associated with improved generalization. Inspired by the…

Machine Learning · Computer Science 2024-12-18 Long Jin , Han Nong , Liangming Chen , Zhenming Su

The rapid scaling of models has led to prohibitively high training and fine-tuning costs. A major factor accounting for memory consumption is the widespread use of stateful optimizers (e.g., Adam), which maintain auxiliary information of…

Machine Learning · Computer Science 2025-06-10 Cong Xu , Wenbin Liang , Mo Yu , Anan Liu , Ke-Yue Zhang , Shunli Wang , Lizhuang Ma , Jianyong Wang , Jun Wang , Wei Zhang

Sharpness-aware minimization (SAM), which searches for flat minima by min-max optimization, has been shown to be useful in improving model generalization. However, since each SAM update requires computing two gradients, its computational…

Machine Learning · Computer Science 2023-05-01 Weisen Jiang , Hansi Yang , Yu Zhang , James Kwok
‹ Prev 1 2 3 10 Next ›