English
Related papers

Related papers: SOAP: Improving and Stabilizing Shampoo using Adam

200 papers

We introduce AdaSub, a stochastic optimization algorithm that computes a search direction based on second-order information in a low-dimensional subspace that is defined adaptively based on available current and past information. Compared…

Optimization and Control · Mathematics 2023-11-08 João Victor Galvão da Mata , Martin S. Andersen

We present a novel sequential Monte Carlo approach to online smoothing of additive functionals in a very general class of path-space models. Hitherto, the solutions proposed in the literature suffer from either long-term numerical…

Computation · Statistics 2022-10-24 Alessandro Mastrototaro , Jimmy Olsson , Johan Alenlöv

Deep reinforcement learning has proven to be a powerful approach to solving control tasks, but its characteristic high-frequency oscillations make it difficult to apply in real-world environments. While prior methods have addressed action…

Machine Learning · Computer Science 2026-01-27 Kyoleen Kwak , Hyoseok Hwang

We propose an efficient ADMM method with guarantees for high-dimensional problems. We provide explicit bounds for the sparse optimization problem and the noisy matrix decomposition problem. For sparse optimization, we establish that the…

Machine Learning · Computer Science 2015-07-08 Hanie Sedghi , Anima Anandkumar , Edmond Jonckheere

In neural network training, RMSProp and Adam remain widely favoured optimisation algorithms. One of the keys to their performance lies in selecting the correct step size, which can significantly influence their effectiveness. Additionally,…

Machine Learning · Computer Science 2024-04-05 Alokendu Mazumder , Rishabh Sabharwal , Manan Tayal , Bhartendu Kumar , Punit Rathore

Extracting the latent information in high-dimensional and incomplete matrices is an important and challenging issue. The Latent Factor Analysis (LFA) model can well handle the high-dimensional matrices analysis. Recently, Particle Swarm…

Machine Learning · Computer Science 2022-08-16 Yuanyi Liu , Jia Chen , Di Wu

Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry and leveraging curvature utilization. Steepest descent algorithms adapt to different…

This paper establishes a mathematical foundation for the Adam optimizer, elucidating its connection to natural gradient descent through Riemannian and information geometry. We provide an accessible and detailed analysis of the diagonal…

Machine Learning · Computer Science 2024-09-05 Dongseong Hwang

In this paper, we introduce a comprehensive framework for developing a machine learning-based SOAP (Subjective, Objective, Assessment, and Plan) classification system without manually SOAP annotated training data or with less manually SOAP…

Computation and Language · Computer Science 2022-11-29 Sunjae Kwon , Zhichao Yang , Hong Yu

Adam is an adaptive gradient method that has experienced widespread adoption due to its fast and reliable training performance. Recent approaches have not offered significant improvement over Adam, often because they do not innovate upon…

Machine Learning · Computer Science 2021-06-11 Brett Daley , Christopher Amato

We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient search techniques to explore an infinite and sparse program…

The Adam optimizer is a cornerstone of modern deep learning, yet the empirical necessity of each of its individual components is often taken for granted. This paper presents a focused investigation into the role of bias-correction, a…

Machine Learning · Computer Science 2025-11-27 Sam Laing , Antonio Orvieto

This paper investigates the accuracy of bootstrap-based inference in the case of long memory fractionally integrated processes. The re-sampling method is based on the semi-parametric sieve approach, whereby the dynamics in the process used…

Methodology · Statistics 2016-03-08 D. S. Poskitt , Simone D. Grose , Gael M. Martin

There is a notable dearth of results characterizing the preconditioning effect of Adam and showing how it may alleviate the curse of ill-conditioning -- an issue plaguing gradient descent (GD). In this work, we perform a detailed analysis…

Machine Learning · Computer Science 2024-02-14 Rudrajit Das , Naman Agarwal , Sujay Sanghavi , Inderjit S. Dhillon

Most large-scale recommender systems follow a multi-stage cascade of retrieval, pre-ranking, ranking, and re-ranking. A key challenge at the pre-ranking stage arises from the heterogeneity of training instances sampled from coarse-grained…

Information Retrieval · Computer Science 2026-03-05 Pengfei Tong , Siyuan Chen , Chenwei Zhang , Bo Wang , Qi Pi , Pixun Li , Zuotao Liu

How does the choice of optimization algorithm shape a model's ability to learn features? To address this question for steepest descent methods --including sign descent, which is closely related to Adam --we introduce steepest mirror flows…

Machine Learning · Computer Science 2026-03-03 Tom Jacobs , Chao Zhou , Rebekka Burkholz

Large Language Models (LLMs) have demonstrated remarkable success across various domains, yet their optimization remains a significant challenge due to the complex and high-dimensional loss landscapes they inhabit. While adaptive optimizers…

Machine Learning · Computer Science 2025-10-13 Liming Liu , Zhenghao Xu , Zixuan Zhang , Hao Kang , Zichong Li , Chen Liang , Weizhu Chen , Tuo Zhao

Recently, Jiang et al. [2026] developed Leon, a practical variant of One-sided Shampoo [Xie et al., 2025a, An et al., 2025] algorithm for online convex optimization, which does not require computing a costly quadratic projection at each…

Optimization and Control · Mathematics 2026-04-06 Dmitry Kovalev

The Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster, more…

Audio and Speech Processing · Electrical Eng. & Systems 2024-04-11 Zengwei Yao , Liyong Guo , Xiaoyu Yang , Wei Kang , Fangjun Kuang , Yifan Yang , Zengrui Jin , Long Lin , Daniel Povey

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

Robotics · Computer Science 2021-12-08 Michael James McDonald , Dylan Hadfield-Menell