English
Related papers

Related papers: Old Optimizer, New Norm: An Anthology

200 papers

Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formulation of model…

Machine Learning · Computer Science 2017-07-06 Miguel Á. Carreira-Perpiñán

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

We investigate the use of regularized Newton methods with adaptive norms for optimizing neural networks. This approach can be seen as a second-order counterpart of adaptive gradient methods, which we here show to be interpretable as…

Machine Learning · Computer Science 2020-09-29 Jonas Kohler , Leonard Adolphs , Aurelien Lucchi

First-order stochastic optimization methods are currently the most widely used class of methods for training deep neural networks. However, the choice of the optimizer has become an ad-hoc rule that can significantly affect the performance.…

Machine Learning · Computer Science 2020-10-21 Samy Jelassi , Aaron Defazio

First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal matrix. Despite the…

Machine Learning · Computer Science 2025-04-30 Damien Martins Gomes

Interpretation of Deep Neural Networks (DNNs) training as an optimal control problem with nonlinear dynamical systems has received considerable attention recently, yet the algorithmic development remains relatively limited. In this work, we…

Machine Learning · Computer Science 2021-06-14 Guan-Horng Liu , Tianrong Chen , Evangelos A. Theodorou

We propose a new approach to learned optimization where we represent the computation of an optimizer's update step using a neural network. The parameters of the optimizer are then learned by training on a set of optimization tasks with the…

Computer Vision and Pattern Recognition · Computer Science 2023-06-29 Erik Gärtner , Luke Metz , Mykhaylo Andriluka , C. Daniel Freeman , Cristian Sminchisescu

Conventional optimization methods in machine learning and controls rely heavily on first-order update rules. Selecting the right method and hyperparameters for a particular task often involves trial-and-error or practitioner intuition,…

Machine Learning · Computer Science 2023-03-31 Tanmay Gautam , Samuel Pfrommer , Somayeh Sojoudi

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

Recent findings indicate that over-parametrization, while crucial for successfully training deep neural networks, also introduces large amounts of redundancy. Tensor methods have the potential to efficiently parametrize over-complete…

Computer Vision and Pattern Recognition · Computer Science 2019-04-05 Jean Kossaifi , Adrian Bulat , Georgios Tzimiropoulos , Maja Pantic

Learning to optimize is an approach that leverages training data to accelerate the solution of optimization problems. Many approaches use unrolling to parametrize the update step and learn optimal parameters. Although L2O has shown…

Optimization and Control · Mathematics 2025-07-15 Patrick Fahy , Mohammad Golbabaee , Matthias J. Ehrhardt

Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradient updates scaled by square roots of exponential moving…

Machine Learning · Computer Science 2019-04-22 Sashank J. Reddi , Satyen Kale , Sanjiv Kumar

The best performing Binary Neural Networks (BNNs) are usually attained using Adam optimization and its multi-step training variants. However, to the best of our knowledge, few studies explore the fundamental reasons why Adam is superior to…

Machine Learning · Computer Science 2021-06-22 Zechun Liu , Zhiqiang Shen , Shichao Li , Koen Helwegen , Dong Huang , Kwang-Ting Cheng

Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without further parameter…

Machine Learning · Computer Science 2023-05-19 Ekin Akyürek , Dale Schuurmans , Jacob Andreas , Tengyu Ma , Denny Zhou

In this thesis we develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive…

Optimization and Control · Mathematics 2014-10-24 Yossi Arjevani

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

Adam-type optimizers, as a class of adaptive moment estimation methods with the exponential moving average scheme, have been successfully used in many applications of deep learning. Such methods are appealing due to the capability on…

Machine Learning · Computer Science 2020-12-17 Bingxin Zhou , Xuebin Zheng , Junbin Gao

The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e.g. it can involve pathological landscapes such as saddle-surfaces…

Machine Learning · Computer Science 2016-08-18 Caglar Gulcehre , Marcin Moczulski , Francesco Visin , Yoshua Bengio

In this work, we propose a new training method for finding minimum weight norm solutions in over-parameterized neural networks (NNs). This method seeks to improve training speed and generalization performance by framing NN training as a…

Machine Learning · Statistics 2018-06-22 Yamini Bansal , Madhu Advani , David D Cox , Andrew M Saxe

Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While various low-memory optimizers have been proposed that…

Machine Learning · Computer Science 2025-03-19 Dayal Singh Kalra , John Kirchenbauer , Maissam Barkeshli , Tom Goldstein