English
Related papers

Related papers: An Isometric Stochastic Optimizer

200 papers

The adaptive optimizer for training neural networks has continually evolved to overcome the limitations of the previously proposed adaptive methods. Recent studies have found the rare counterexamples that Adam cannot converge to the optimal…

Machine Learning · Computer Science 2019-11-04 Kiwook Bae , Heechang Ryu , Hayong Shin

The stochastic gradient descent (SGD) optimizers are generally used to train the convolutional neural networks (CNNs). In recent years, several adaptive momentum based SGD optimizers have been introduced, such as Adam, diffGrad, Radam and…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Shiv Ram Dubey , Satish Kumar Singh , Bidyut Baran Chaudhuri

In this work, we study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new stochastic family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps…

Machine Learning · Computer Science 2025-06-09 Thomas Pethick , Wanyun Xie , Kimon Antonakopoulos , Zhenyu Zhu , Antonio Silveti-Falls , Volkan Cevher

Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is…

Machine Learning · Computer Science 2025-03-03 Rosie Zhao , Depen Morwani , David Brandfonbrener , Nikhil Vyas , Sham Kakade

The success of the Adam optimizer on a wide array of architectures has made it the default in settings where stochastic gradient descent (SGD) performs poorly. However, our theoretical understanding of this discrepancy is lagging,…

Machine Learning · Computer Science 2023-04-28 Frederik Kunstner , Jacques Chen , Jonathan Wilder Lavington , Mark Schmidt

In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural…

Optimization and Control · Mathematics 2023-11-08 Haochuan Li , Alexander Rakhlin , Ali Jadbabaie

Adam is a widely used optimizer in neural network training due to its adaptive learning rate. However, because different data samples influence model updates to varying degrees, treating them equally can lead to inefficient convergence. To…

Machine Learning · Statistics 2025-12-09 Gyu Yeol Kim , Min-hwan Oh

While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers. In this work, we leverage the same scaling approach behind the success of deep learning to…

This work addresses the instability in asynchronous data parallel optimization. It does so by introducing a novel distributed optimizer which is able to efficiently optimize a centralized model under communication constraints. The optimizer…

Machine Learning · Statistics 2017-10-09 Joeri Hermans , Gerasimos Spanakis , Rico Möckel

Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g. Adam) and accelerated schemes (e.g. stochastic gradient descent (SGD) with momentum). For many models such as convolutional neural networks…

Machine Learning · Computer Science 2020-12-22 Juntang Zhuang , Tommy Tang , Yifan Ding , Sekhar Tatikonda , Nicha Dvornek , Xenophon Papademetris , James S. Duncan

Adaptive moment methods such as Adam use a diagonal, coordinate-wise preconditioner based on exponential moving averages of squared gradients. This diagonal scaling is coordinate-system dependent and can struggle with dense or rotated…

Machine Learning · Computer Science 2026-04-09 Devender Singh , Tarun Sheel

The choice of optimiser is important in deep learning, as it strongly influences model efficiency and speed of convergence. However, many commonly used optimisers encounter difficulties when applied to imbalanced and sequential datasets,…

Solving semiparametric models can be computationally challenging because the dimension of parameter space may grow large with increasing sample size. Classical Newton's method becomes quite slow and unstable with intensive calculation of…

Computation · Statistics 2021-08-19 Yucong Lin , Jinhua Su , Yang Liu , Jue Hou , Feifei Wang

Stochastic gradient descent (SGD) is the main approach for training deep networks: it moves towards the optimum of the cost function by iteratively updating the parameters of a model in the direction of the gradient of the loss evaluated on…

Machine Learning · Computer Science 2021-03-30 Loris Nanni , Gianluca Maguolo , Alessandra Lumini

The optimization algorithm and its hyperparameters can significantly affect the training speed and resulting model accuracy in machine learning applications. The wish list for an ideal optimizer includes fast and smooth convergence to low…

Machine Learning · Computer Science 2024-02-20 Marco Eckhoff , Markus Reiher

Time-series forecasting often faces challenges from non-stationarity, particularly distributional drift, where the data distribution evolves over time. This dynamic behavior can undermine the effectiveness of adaptive optimizers, such as…

Machine Learning · Computer Science 2026-03-12 Yuze Dong , Jinsong Wu

Progress in deep learning is slowed by the days or weeks it takes to train large models. The natural solution of using more hardware is limited by diminishing returns, and leads to inefficient use of additional resources. In this paper, we…

Machine Learning · Computer Science 2017-12-12 Shankar Krishnan , Ying Xiao , Rif A. Saurous

Despite their popularity in deep learning and machine learning in general, the theoretical properties of adaptive optimizers such as Adagrad, RMSProp, Adam or AdamW are not yet fully understood. In this paper, we develop a novel framework…

Machine Learning · Computer Science 2022-11-09 Han Nguyen , Hai Pham , Sashank J. Reddi , Barnabás Póczos

The empirical success of machine learning models with many more parameters than measurements has generated an interest in the theory of overparameterisation, i.e., underdetermined models. This paradigm has recently been studied in domains…

An AI assessor is an external, ideally indepen-dent system that predicts an indicator, e.g., a loss value, of another AI system. Assessors can lever-age information from the test results of many other AI systems and have the flexibility of…

Machine Learning · Computer Science 2025-02-04 Daniel Romero-Alvarado , Fernando Martínez-Plumed , José Hernández-Orallo