English
Related papers

Related papers: Adafactor: Adaptive Learning Rates with Sublinear …

200 papers

Stochastic optimization algorithms using exponential moving averages of the past gradients, such as ADAM, RMSProp and AdaGrad, have been having great successes in many applications, especially in training deep neural networks. ADAM in…

Machine Learning · Computer Science 2026-01-30 Ruiqi Wang , Diego Klabjan

Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost…

Computation and Language · Computer Science 2022-11-03 Yaqing Wang , Sahaj Agarwal , Subhabrata Mukherjee , Xiaodong Liu , Jing Gao , Ahmed Hassan Awadallah , Jianfeng Gao

Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost…

Computation and Language · Computer Science 2022-11-07 Yaqing Wang , Sahaj Agarwal , Subhabrata Mukherjee , Xiaodong Liu , Jing Gao , Ahmed Hassan Awadallah , Jianfeng Gao

For solving pseudo-convex global optimization problems, we present a novel fully adaptive steepest descent method (or ASDM) without any hard-to-estimate parameters. For the step-size regulation in an $\varepsilon$-normalized direction, we…

Optimization and Control · Mathematics 2021-08-12 Z. R. Gabidullina

Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses with models over-parameterized enough to interpolate the data.…

Machine Learning · Computer Science 2021-02-22 Sharan Vaswani , Issam Laradji , Frederik Kunstner , Si Yi Meng , Mark Schmidt , Simon Lacoste-Julien

Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gradient splitting, but its static hyperparameters -- the subspace ratio ($\rho$) and update…

Machine Learning · Computer Science 2026-04-30 Quang-Hung Bui , Anh Son Ta

Adaptive gradient methods for stochastic optimization adjust the learning rate for each parameter locally. However, there is also a global learning rate which must be tuned in order to get the best performance. In this paper, we present a…

Machine Learning · Computer Science 2018-06-12 Hiroaki Hayashi , Jayanth Koushik , Graham Neubig

The era of huge data necessitates highly efficient machine learning algorithms. Many common machine learning algorithms, however, rely on computationally intensive subroutines that are prohibitively expensive on large datasets. Oftentimes,…

Machine Learning · Computer Science 2023-09-26 Mo Tiwari

The learning rate is a crucial hyperparameter in deep learning, with its ideal value depending on the problem and potentially changing during training. In this paper, we investigate the practical utility of adaptive learning rate mechanisms…

Machine Learning · Computer Science 2025-08-08 Asma Atamna , Tom Maus , Fabian Kievelitz , Tobias Glasmachers

The paper derives analytical expressions for the asymptotic average updating direction of the adaptive moment generation (ADAM) algorithm when applied to recursive identification of nonlinear systems. It is proved that the standard…

Systems and Control · Electrical Eng. & Systems 2025-10-24 Torbjörn Wigren , Ruoqi Zhang , Per Mattsson

This work presents a new method for online selection of multiple penalty parameters for the alternating direction method of multipliers (ADMM) algorithm applied to optimization problems with multiple constraints or functionals with block…

Image and Video Processing · Electrical Eng. & Systems 2026-04-21 Luke Lozenski , Michael T. McCann , Brendt Wohlberg

While vision-and-language models significantly advance in many fields, the challenge of continual learning is unsolved. Parameter-efficient modules like adapters and prompts present a promising way to alleviate catastrophic forgetting.…

Machine Learning · Computer Science 2024-10-16 Hong Li , Zhiquan Tan , Xingyu Li , Weiran Huang

Two major momentum-based techniques that have achieved tremendous success in optimization are Polyak's heavy ball method and Nesterov's accelerated gradient. A crucial step in all momentum-based methods is the choice of the momentum…

Machine Learning · Statistics 2017-12-21 Vishwak Srinivasan , Adepu Ravi Sankar , Vineeth N Balasubramanian

We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems from multiple fields, including classification and…

Machine Learning · Computer Science 2021-08-27 Aaron Defazio , Samy Jelassi

Stochastic gradient descent (SGD) and its many variants are the widespread optimization algorithms for training deep neural networks. However, SGD suffers from inevitable drawbacks, including vanishing gradients, lack of theoretical…

Machine Learning · Computer Science 2024-01-09 Zeinab Ebrahimi , Gustavo Batista , Mohammad Deghat

This paper presents a new parameter estimation algorithm for the adaptive control of a class of time-varying plants. The main feature of this algorithm is a matrix of time-varying learning rates, which enables parameter estimation error…

Optimization and Control · Mathematics 2021-11-18 Joseph E. Gaudio , Anuradha M. Annaswamy , Eugene Lavretsky , Michael A. Bolender

Alternating Direction Method of Multipliers (ADMM) is a popular method for solving large-scale Machine Learning problems. Stochastic ADMM was proposed to reduce the per iteration computational complexity, which is more suitable for big data…

Numerical Analysis · Computer Science 2023-04-25 Chao Zhang , Zebang Shen , Hui Qian , Tengfei Zhou , Jianya Zhou , Jianying Zhou

An algorithm is presented for momentum gradient descent optimization based on the first-order differential equation of the Newtonian dynamics. The fictitious mass is introduced to the dynamics of momentum for regularizing the adaptive…

Machine Learning · Computer Science 2018-05-15 Zhidong Han

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

Machine Learning · Computer Science 2020-05-26 Mohammed Sharafath Abdul Hameed , Gavneet Singh Chadha , Andreas Schwung , Steven X. Ding

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Machine Learning · Computer Science 2026-03-30 Alireza Moayedikia , Alicia Troncoso