English
Related papers

Related papers: EMA-Nesterov: Stabilizing Nesterov's Lookahead for…

200 papers

Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge…

Machine Learning · Computer Science 2022-09-23 James Harrison , Luke Metz , Jascha Sohl-Dickstein

Recent advances in deep learning optimization showed that, with some a-posteriori information on fully-trained models, it is possible to match the same performance by simply training a subset of their parameters. Such a discovery has a…

Machine Learning · Computer Science 2022-11-15 Andrea Bragagnolo , Enzo Tartaglione , Marco Grangetto

The expectation-maximization (EM) algorithm is a well-known iterative method for computing maximum likelihood estimates from incomplete data. Despite its numerous advantages, a main drawback of the EM algorithm is its frequently observed…

Computation · Statistics 2018-08-14 Nicholas C. Henderson , Ravi Varadhan

Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control settings. These zeroth-order optimizers require sampling a…

Machine Learning · Computer Science 2021-12-16 Kevin Huang , Sahin Lale , Ugo Rosolia , Yuanyuan Shi , Anima Anandkumar

Multimarginal optimal transport (MOT) is a powerful framework for modeling interactions between multiple distributions, yet its applicability is bottlenecked by a high computational overhead. Entropic regularization provides computational…

Machine Learning · Computer Science 2025-06-03 Dor Tsur , Ziv Goldfeld , Kristjan Greenewald , Haim Permuter

Stochastic gradient descent (SGD) with stochastic momentum is popular in nonconvex stochastic optimization and particularly for the training of deep neural networks. In standard SGD, parameters are updated by improving along the path of the…

Machine Learning · Computer Science 2021-06-08 Jun-Kun Wang , Chi-Heng Lin , Jacob Abernethy

Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given…

Machine Learning · Computer Science 2023-05-29 Marcin Pietron , Dominik Zurek , Kamil Faber , Roberto Corizzo

Neural-ODE parameterize a differential equation using continuous depth neural network and solve it using numerical ODE-integrator. These models offer a constant memory cost compared to models with discrete sequence of hidden layers in which…

Machine Learning · Computer Science 2025-03-27 Sheikh Waqas Akhtar

Recently algorithms incorporating second order curvature information have become popular in training neural networks. The Nesterov's Accelerated Quasi-Newton (NAQ) method has shown to effectively accelerate the BFGS quasi-Newton method by…

Machine Learning · Computer Science 2020-10-16 Sota Yasuda , Shahrzad Mahboubi , S. Indrapriyadarsini , Hiroshi Ninomiya , Hideki Asai

Recent advances have reformulated diffusion models as deterministic ordinary differential equations (ODEs) through the framework of flow matching, providing a unified formulation for the noise-to-data generative process. Various…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Yan Luo , Henry Huang , Todd Y. Zhou , Mengyu Wang

Training networks consisting of biophysically accurate neuron models could allow for new insights into how brain circuits can organize and solve tasks. We begin by analyzing the extent to which the central algorithm for neural network…

Neurons and Cognition · Quantitative Biology 2023-11-22 James Hazelden , Yuhan Helena Liu , Eli Shlizerman , Eric Shea-Brown

Within the current sphere of deep learning research, despite the extensive application of optimization algorithms such as Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (Adam), there remains a pronounced inadequacy in…

Machine Learning · Computer Science 2025-10-30 Zhifeng Wang , Longlong Li , Chunyan Zeng

In this paper, we present a cross-entropy optimization method for hyperparameter optimization in stochastic gradient-based approaches to train deep neural networks. The value of a hyperparameter of a learning algorithm often has great…

Machine Learning · Computer Science 2024-09-17 Kevin Li , Fulu Li

In the area of learning-driven artificial intelligence advancement, the integration of machine learning (ML) into self-driving (SD) technology stands as an impressive engineering feat. Yet, in real-world applications outside the confines of…

Robotics · Computer Science 2023-09-06 Haozhe Lei , Quanyan Zhu

In this work we propose a differential geometric motivation for Nesterov's accelerated gradient method (AGM) for strongly-convex problems. By considering the optimization procedure as occurring on a Riemannian manifold with a natural…

Machine Learning · Computer Science 2019-11-21 Aaron Defazio

This paper investigates a class of stochastic bilevel optimization problems where the upper-level function is nonconvex with potentially unbounded smoothness and the lower-level problem is strongly convex. These problems have significant…

Machine Learning · Computer Science 2025-01-16 Xiaochuan Gong , Jie Hao , Mingrui Liu

Overshoot is a novel, momentum-based stochastic gradient descent optimization method designed to enhance performance beyond standard and Nesterov's momentum. In conventional momentum methods, gradients from previous steps are aggregated…

Machine Learning · Computer Science 2025-01-17 Jakub Kopal , Michal Gregor , Santiago de Leon-Martinez , Jakub Simko

Data augmentation (DA) has been widely used to improve the generalization of deep neural networks. While existing DA methods have proven effective, they often rely on augmentation operations with random magnitudes to each sample. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Suorong Yang , Furao Shen , Jian Zhao

Neuroevolution is one of the methodologies that can be used for learning optimal architecture during training. It uses evolutionary algorithms to generate the topology of artificial neural networks and its parameters. The main benefits are…

Neural and Evolutionary Computing · Computer Science 2022-08-30 M. Pietroń , D. Żurek , K. Faber , R. Corizzo

Asynchronous optimization algorithms often require delay bounds to prove their convergence, though these bounds can be difficult to obtain in practice. Existing algorithms that do not require delay bounds often converge slowly. Therefore,…

Optimization and Control · Mathematics 2025-08-12 Ellie Pond , Yichen Zhao , Matthew Hale