English
Related papers

Related papers: Hyperparameter Transfer Enables Consistent Gains o…

200 papers

The training of diffusion models is often absent in the evaluation of new optimization techniques. In this work, we benchmark recent optimization algorithms for training a diffusion model for denoising flow trajectories. We observe that…

Machine Learning · Computer Science 2025-10-23 Fabian Schaipp

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

Scaling model sizes to scale performance has worked remarkably well for the current large language models paradigm. The research and empirical findings of various scaling studies led to novel scaling results and laws that guides subsequent…

A range of recent optimizers have emerged that approximate the same "matrix-whitening" transformation in various ways. In this work, we systematically deconstruct such optimizers, aiming to disentangle the key components that explain…

Machine Learning · Computer Science 2025-10-30 Kevin Frans , Pieter Abbeel , Sergey Levine

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

Foundation models excel across diverse tasks, but adapting them to specialized applications often requires fine-tuning, an approach that is memory and compute-intensive. Parameter-efficient fine-tuning (PEFT) methods mitigate this by…

Machine Learning · Computer Science 2026-04-24 Abel Gurung , Joseph Campbell

After developer adjustments to a machine learning (ML) algorithm, how can the results of an old hyperparameter optimization (HPO) automatically be used to speedup a new HPO? This question poses a challenging problem, as developer…

Machine Learning · Computer Science 2020-10-27 Danny Stoll , Jörg K. H. Franke , Diane Wagner , Simon Selg , Frank Hutter

Deeper modern architectures are costly to train, making hyperparameter transfer preferable to expensive repeated tuning. Maximal Update Parametrization ($\mu$P) helps explain why many hyperparameters transfer across width. Yet depth scaling…

Machine Learning · Computer Science 2026-02-10 Shenxi Wu , Haosong Zhang , Xingjian Ma , Shirui Bian , Yichi Zhang , Xi Chen , Wei Lin

In this work, we take an experimentally grounded look at neural network optimization. Building on the Shampoo family of algorithms, we identify and alleviate three key issues, resulting in the proposed SPlus method. First, we find that…

Machine Learning · Computer Science 2025-10-27 Kevin Frans , Sergey Levine , Pieter Abbeel

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

Scaling laws have made language-model performance predictable from model size, data, and compute, but they typically treat the optimizer as a fixed training detail. We show that this assumption misses a fundamental axis of representation…

Machine Learning · Computer Science 2026-05-22 Nandan Kumar Jha , Brandon Reagen

Recent frontier large language models predominantly rely on Mixture-of-Experts (MoE) architectures. Despite empirical progress, there is still no principled understanding of how hyperparameters should scale with network width $N$, expert…

Machine Learning · Computer Science 2026-05-15 Leena Chennuru Vankadara , Moritz Haas , Luke Hayward , Sebastian Bordt , Alessandro Breccia

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter…

Machine Learning · Computer Science 2018-04-13 Noam Shazeer , Mitchell Stern

Shampoo-based methods, such as KL-Shampoo and SOAP, have demonstrated strong performance in training neural networks and rely on QR decomposition. Because existing QR implementations require single-precision (FP32) arithmetic and remain…

Machine Learning · Computer Science 2026-05-27 Alan Milligan , Zikun Xu , Simon Lacoste-Julien , Felix Dangel , Wu Lin

Efficient LLM pre-training requires well-tuned hyperparameters (HPs), including learning rate $\eta$ and weight decay $\lambda$. We study scaling laws for HPs: formulas for how to scale HPs as we scale model size N, dataset size D, and…

Machine Learning · Computer Science 2025-11-25 Shane Bergsma , Nolan Dey , Gurpreet Gosal , Gavia Gray , Daria Soboleva , Joel Hestness

Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the normalization-induced scale invariance among the weights…

Machine Learning · Computer Science 2021-01-19 Byeongho Heo , Sanghyuk Chun , Seong Joon Oh , Dongyoon Han , Sangdoo Yun , Gyuwan Kim , Youngjung Uh , Jung-Woo Ha

The prevailing paradigm in large language model (LLM) development is to pretrain a base model, then perform further training to improve performance and model behavior. However, hyperparameter optimization and scaling laws have been studied…

Machine Learning · Computer Science 2026-02-12 Tessa Han , Sebastian Bordt , Hanlin Zhang , Sham Kakade

Training large language models requires optimization algorithms that are not only statistically effective, but also computationally and memory efficient at extreme scale. Although Adam remains the dominant optimizer for large-scale…

Machine Learning · Computer Science 2026-05-12 Aditya Ranganath

Deep learning models have become a cornerstone of modern AI research, yet their initializations and learning rates may at times be set in an opaque or ad-hoc fashion due to the high cost of hyperparameter sweeps. The $\mu$-Parameterization…

Machine Learning · Computer Science 2025-02-17 Lucas Lingle

Shampoo with Adam in the Preconditioner's eigenbasis (SOAP) has recently emerged as a promising optimization algorithm for neural network training, achieving superior training efficiency over both Adam and Shampoo in language modeling…

Machine Learning · Computer Science 2025-09-30 Yanqing Lu , Letao Wang , Jinbo Liu