English
Related papers

Related papers: The Surprising Agreement Between Convex Optimizati…

200 papers

Deep learning models require a large amount of data to perform well. When data is scarce for a target task, we can transfer the knowledge gained by training on similar tasks to quickly learn the target. A successful approach is…

Machine Learning · Computer Science 2021-03-18 Alberto Bernacchia

The performance of an optimizer on large-scale deep learning models depends critically on fine-tuning the learning rate, often requiring an extensive grid search over base learning rates, schedules, and other hyperparameters. In this paper,…

Machine Learning · Computer Science 2025-06-11 Ruichen Jiang , Ali Kavis , Aryan Mokhtari

Neural scaling laws, which in some domains can predict the performance of large neural networks as a function of model, data, and compute scale, are the cornerstone of building foundation models in Natural Language Processing and Computer…

Machine Learning · Computer Science 2026-03-27 Shashank Subramanian , Alexander Kiefer , Arnur Nigmetov , Amir Gholami , Dmitriy Morozov , Michael W. Mahoney

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to restart the process over again once new data becomes available. A much cheaper and more efficient solution would be to enable the continual pre-training…

Computation and Language · Computer Science 2023-09-08 Kshitij Gupta , Benjamin Thérien , Adam Ibrahim , Mats L. Richter , Quentin Anthony , Eugene Belilovsky , Irina Rish , Timothée Lesort

Large language models are increasingly trained in continual or open-ended settings, where the total training horizon is not known in advance. Despite this, most existing pretraining recipes are not anytime: they rely on horizon-dependent…

Machine Learning · Computer Science 2026-02-04 Alexandru Meterez , Pranav Ajit Nair , Depen Morwani , Cengiz Pehlevan , Sham Kakade

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of…

Machine Learning · Computer Science 2025-10-28 Ran Levinstein , Amit Attia , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Itay Evron

Inspired by recent research that recommends starting neural networks training with large learning rates (LRs) to achieve the best generalization, we explore this hypothesis in detail. Our study clarifies the initial LR ranges that provide…

Machine Learning · Computer Science 2023-11-21 Ekaterina Lobacheva , Eduard Pockonechnyy , Maxim Kodryan , Dmitry Vetrov

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Gengwei Zhang , Liyuan Wang , Guoliang Kang , Ling Chen , Yunchao Wei

Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of…

Machine Learning · Statistics 2018-06-04 Jack Umenberger , Thomas B. Schön

We study how the learning rate affects the performance of a relaxed randomized Kaczmarz algorithm for solving $A x \approx b + \varepsilon$, where $A x =b$ is a consistent linear system and $\varepsilon$ has independent mean zero random…

Numerical Analysis · Mathematics 2022-08-10 Nicholas F. Marshall , Oscar Mickelin

Within the scaling laws paradigm, which underpins the training of large neural networks like ChatGPT and Llama, we consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon, a…

Machine Learning · Computer Science 2024-10-10 Elvis Dohmatob , Yunzhen Feng , Arjun Subramonian , Julia Kempe

Fine-tuning large language models (LLMs) for reasoning tasks using reinforcement learning methods like Group Relative Policy Optimization (GRPO) is computationally expensive. To address this, we propose a predictive framework that models…

Machine Learning · Computer Science 2026-03-23 Datta Nimmaturi , Vaishnavi Bhargava , Rajat Ghosh , Johnu George , Debojyoti Dutta

Large Language Models (LLMs) have demonstrated remarkable performance across diverse domains. However, effectively leveraging their vast knowledge for training smaller downstream models remains an open challenge, especially in domains like…

Machine Learning · Computer Science 2025-07-28 Davor Vukadin , Marin Šilić , Goran Delač

In practice, the hyperparameters $(\beta_1, \beta_2)$ and weight-decay $\lambda$ in AdamW are typically kept at fixed values. Is there any reason to do otherwise? We show that for large-scale language model training, the answer is yes: by…

Machine Learning · Statistics 2026-02-19 Damien Ferbach , Courtney Paquette , Gauthier Gidel , Katie Everett , Elliot Paquette

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on…

Computation and Language · Computer Science 2024-10-04 Constanza Fierro , Jiaang Li , Anders Søgaard

We analyze the convergence behavior of stochastic gradient descent with momentum (SGDM) under dynamic learning-rate and batch-size schedules by introducing a novel and simpler Lyapunov function. We extend the existing theoretical framework…

Machine Learning · Computer Science 2025-10-13 Yuichi Kondo , Hideaki Iiduka

As we scale to more massive machine learning models, the frequent synchronization demands inherent in data-parallel approaches create significant slowdowns, posing a critical challenge to further scaling. Recent work develops an approach…

Machine Learning · Computer Science 2025-03-14 Zachary Charles , Gabriel Teston , Lucio Dery , Keith Rush , Nova Fallen , Zachary Garrett , Arthur Szlam , Arthur Douillard

The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedules (constant and then cut) are widely used in practice…

Optimization and Control · Mathematics 2021-02-19 Xiaoyu Wang , Sindri Magnússon , Mikael Johansson

The increasing reliance on numerical methods for controlling dynamical systems and training machine learning models underscores the need to devise algorithms that dependably and efficiently navigate complex optimization landscapes.…

Systems and Control · Electrical Eng. & Systems 2024-06-04 Andrea Martin , Luca Furieri

A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and…

Machine Learning · Computer Science 2022-10-17 Ruohan Wang , Marco Ciccone , Giulia Luise , Andrew Yapp , Massimiliano Pontil , Carlo Ciliberto
‹ Prev 1 3 4 5 6 7 10 Next ›