English
Related papers

Related papers: Stabilizing Backpropagation in 16-bit Neural Train…

200 papers

Traditional analyses of gradient descent optimization show that, when the largest eigenvalue of the loss Hessian - often referred to as the sharpness - is below a critical learning-rate threshold, then training is 'stable' and training loss…

Machine Learning · Computer Science 2024-12-24 Lawrence Wang , Stephen J. Roberts

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…

Machine Learning · Computer Science 2026-05-14 Lilin Zhang , Yimo Guo , Yue Li , Jiancheng Shi , Xianggen Liu

The disparity between the computational demands of deep learning and the capabilities of compute hardware is expanding drastically. Although deep learning achieves remarkable performance in countless tasks, its escalating requirements for…

Machine Learning · Computer Science 2025-09-12 Xiao Wang , Hendrik Borras , Bernhard Klein , Holger Fröning

The advent of quantum computing holds the potential to revolutionize various fields by solving complex problems more efficiently than classical computers. Despite this promise, practical quantum advantage is hindered by current hardware…

Quantum Physics · Physics 2024-08-06 William Troy

Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer blocks, trading additional computation for improved performance without…

Machine Learning · Computer Science 2026-05-26 Rao Fu , Zixuan Yang , Jiankun Zhang , Jing Ma , Hechang Chen , Yu Li , Yi Chang

It is known that the standard stochastic gradient descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as,…

Optimization and Control · Mathematics 2024-06-21 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

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

Despite the considerable success of neural networks in security settings such as malware detection, such models have proved vulnerable to evasion attacks, in which attackers make slight changes to inputs (e.g., malware) to bypass detection.…

Machine Learning · Computer Science 2021-06-09 Netanel Raviv , Aidan Kelley , Michael Guo , Yevgeny Vorobeychik

In this paper, we study the convergence of the Adaptive Moment Estimation (Adam) algorithm under unconstrained non-convex smooth stochastic optimizations. Despite the widespread usage in machine learning areas, its theoretical properties…

Optimization and Control · Mathematics 2023-11-06 Yusu Hong , Junhong Lin

The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Existing convergence theories for adaptive optimizers, however,…

Machine Learning · Computer Science 2026-03-03 Xuan Tang , Jichu Li , Difan Zou

Mixed-signal artificial neural networks (ANNs) that employ analog matrix-multiplication accelerators can achieve higher speed and improved power efficiency. Though analog computing is known to be susceptible to noise and device…

Signal Processing · Electrical Eng. & Systems 2021-07-01 Joseph Ulseth , Zheyuan Zhu , Guifang Li , Shuo Pang

Here I present a small update to the bias-correction term in the Adam optimizer that has the advantage of making smaller gradient updates in the first several steps of training. With the default bias-correction, Adam may actually make…

Machine Learning · Computer Science 2021-10-25 John St John

Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing. However, deploying NNs in resource-constrained safety-critical systems has challenges due to uncertainty in the…

Machine Learning · Computer Science 2024-01-17 Soyed Tuhin Ahmed

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

Nondeterminism in neural network optimization produces uncertainty in performance, making small improvements difficult to discern from run-to-run variability. While uncertainty can be reduced by training multiple model copies, doing so is…

Machine Learning · Computer Science 2021-07-13 Cecilia Summers , Michael J. Dinneen

A lack of software reproducibility has become increasingly apparent in the last several years, calling into question the validity of scientific findings affected by published tools. Reproducibility issues may have numerous sources of error,…

Neurons and Cognition · Quantitative Biology 2020-04-23 Gregory Kiar , Pablo de Oliveira Castro , Pierre Rioux , Eric Petit , Shawn T. Brown , Alan C. Evans , Tristan Glatard

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Machine Learning · Computer Science 2026-05-08 Alaa Zniber , Ouassim Karrakchou , Mounir Ghogho

Deep Learning has revolutionized machine learning and artificial intelligence, achieving superhuman performance in several standard benchmarks. It is well-known that deep learning models are inefficient to train; they learn by processing…

Machine Learning · Computer Science 2021-12-03 Fartash Faghri

Physics-informed neural networks (PINNs) have gained prominence in recent years and are now effectively used in a number of applications. However, their performance remains unstable due to the complex landscape of the loss function. To…

Machine Learning · Computer Science 2025-09-30 Dmitry Bylinkin , Mikhail Aleksandrov , Savelii Chezhegov , Aleksandr Beznosikov

In recent years, deep learning has achieved remarkable success in various fields such as image recognition, natural language processing, and speech recognition. The effectiveness of deep learning largely depends on the optimization methods…

Machine Learning · Computer Science 2023-04-25 David Shulman
‹ Prev 1 8 9 10 Next ›