English
Related papers

Related papers: 4-bit Shampoo for Memory-Efficient Network Trainin…

200 papers

Preconditioned stochastic optimization algorithms, exemplified by Shampoo, outperform first-order optimizers by offering theoretical convergence benefits and practical gains in large-scale neural network training. However, they incur…

Machine Learning · Computer Science 2025-03-13 Jingyang Li , Kuangyu Ding , Kim-Chuan Toh , Pan Zhou

Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matrices. We describe and analyze a new structure-aware…

Machine Learning · Computer Science 2018-03-05 Vineet Gupta , Tomer Koren , Yoram Singer

Shampoo is one of the leading approximate second-order optimizers: a variant of it has won the MLCommons AlgoPerf competition, and it has been shown to produce models with lower activation outliers that are easier to compress. Yet, applying…

Machine Learning · Computer Science 2026-02-03 Ionut-Vlad Modoranu , Philip Zmushko , Erik Schultheis , Mher Safaryan , Dan Alistarh

Optimizer states are a major source of memory consumption for training neural networks, limiting the maximum trainable model within given memory budget. Compressing the optimizer states from 32-bit floating points to lower bitwidth is…

Machine Learning · Computer Science 2023-10-30 Bingrui Li , Jianfei Chen , Jun Zhu

Shampoo, a second-order optimization algorithm which uses a Kronecker product preconditioner, has recently garnered increasing attention from the machine learning community. The preconditioner used by Shampoo can be viewed either as an…

Machine Learning · Computer Science 2024-06-26 Depen Morwani , Itai Shapira , Nikhil Vyas , Eran Malach , Sham Kakade , Lucas Janson

Second-order optimization has been developed to accelerate the training of deep neural networks and it is being applied to increasingly larger-scale models. In this study, towards training on further larger scales, we identify a specific…

Machine Learning · Computer Science 2024-06-11 Satoki Ishikawa , Ryo Karakida

There is growing evidence of the effectiveness of Shampoo, a higher-order preconditioning method, over Adam in deep learning optimization tasks. However, Shampoo's drawbacks include additional hyperparameters and computational overhead when…

Machine Learning · Computer Science 2025-02-03 Nikhil Vyas , Depen Morwani , Rosie Zhao , Mujin Kwun , Itai Shapira , David Brandfonbrener , Lucas Janson , Sham Kakade

Optimizers leveraging the matrix structure in neural networks, such as Shampoo and Muon, are more data-efficient than element-wise algorithms like Adam and Signum. While in specific settings, Shampoo and Muon reduce to spectral descent…

Machine Learning · Computer Science 2026-02-11 Runa Eschenhagen , Anna Cai , Tsung-Hsien Lee , Hao-Jun Michael Shi

Second-order methods hold significant promise for enhancing the convergence of deep neural network training; however, their large memory and computational demands have limited their practicality. Thus there is a need for scalable…

Machine Learning · Computer Science 2023-11-17 Fnu Devvrit , Sai Surya Duvvuri , Rohan Anil , Vineet Gupta , Cho-Jui Hsieh , Inderjit Dhillon

Second order stochastic optimizers allow parameter update step size and direction to adapt to loss curvature, but have traditionally required too much memory and compute for deep learning. Recently, Shampoo [Gupta et al., 2018] introduced a…

Machine Learning · Statistics 2023-06-01 Jonathan Mei , Alexander Moreno , Luke Walters

We present a novel unified analysis for a broad class of adaptive optimization algorithms with structured (e.g., layerwise, diagonal, and kronecker-factored) preconditioners for both online regret minimization and offline convex…

Machine Learning · Computer Science 2025-07-16 Shuo Xie , Tianhao Wang , Sashank Reddi , Sanjiv Kumar , Zhiyuan Li

Optimization in machine learning, both theoretical and applied, is presently dominated by first-order gradient methods such as stochastic gradient descent. Second-order optimization methods, that involve second derivatives and/or second…

Machine Learning · Computer Science 2021-03-08 Rohan Anil , Vineet Gupta , Tomer Koren , Kevin Regan , Yoram Singer

Several recently introduced deep learning optimizers utilizing matrix-level preconditioning have shown promising speedups relative to the current dominant optimizer AdamW, particularly in relatively small-scale experiments. However, efforts…

Machine Learning · Computer Science 2026-01-21 Shikai Qiu , Zixi Chen , Hoang Phan , Qi Lei , Andrew Gordon Wilson

The recent success of Shampoo in the AlgoPerf contest has sparked renewed interest in Kronecker-factorization-based optimization algorithms for training neural networks. Despite its success, Shampoo relies heavily on several heuristics such…

Machine Learning · Computer Science 2025-10-30 Runa Eschenhagen , Aaron Defazio , Tsung-Hsien Lee , Richard E. Turner , Hao-Jun Michael Shi

As new optimizers gain traction and model quantization becomes standard for efficient deployment, a key question arises: how does the choice of optimizer affect model performance in the presence of quantization? Despite progress in both…

Machine Learning · Computer Science 2025-10-03 Georgios Vlassis , Saleh Ashkboos , Alexandra Volkova , Torsten Hoefler , Dan Alistarh

Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural network training. However, existing 4-bit training methods require custom numerical formats which are not supported by contemporary hardware. In this…

Machine Learning · Computer Science 2023-06-26 Haocheng Xi , Changhao Li , Jianfei Chen , Jun Zhu

Second-order optimization algorithms exhibit excellent convergence properties for training deep learning models, but often incur significant computation and memory overheads. This can result in lower training efficiency than the first-order…

Machine Learning · Computer Science 2023-08-07 Lin Zhang , Shaohuai Shi , Bo Li

Training learned image compression (LIC) models entails navigating a challenging optimization landscape defined by the fundamental trade-off between rate and distortion. Standard first-order optimizers, such as SGD and Adam, struggle with…

Image and Video Processing · Electrical Eng. & Systems 2026-01-30 Yichi Zhang , Fengqing Zhu

Second-order optimization methods, which leverage curvature information, offer faster and more stable convergence than first-order methods such as stochastic gradient descent (SGD) and Adam. However, their practical adoption is hindered by…

Emerging Technologies · Computer Science 2025-12-08 Saitao Zhang , Yubiao Luo , Shiqing Wang , Pushen Zuo , Yongxiang Li , Lunshuai Pan , Zheng Miao , Zhong Sun

Despite their better convergence properties compared to first-order optimizers, second-order optimizers for deep learning have been less popular due to their significant computational costs. The primary efficiency bottleneck in such…

Machine Learning · Computer Science 2023-10-30 Siddharth Singh , Zachary Sating , Abhinav Bhatele
‹ Prev 1 2 3 10 Next ›