English
Related papers

Related papers: Small-scale proxies for large-scale Transformer tr…

200 papers

We consider the problem of retraining machine learning (ML) models when new batches of data become available. Existing approaches greedily optimize for predictive power independently at each batch, without considering the stability of the…

Machine Learning · Computer Science 2025-02-05 Dimitris Bertsimas , Vassilis Digalakis , Yu Ma , Phevos Paschalidis

We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of…

Systems and Control · Computer Science 2018-10-30 Ming Jin , Javad Lavaei

Pretraining of large language models is not only expensive but also prone to certain training instabilities. A specific instability that often occurs at the end of training is output logit divergence. The most widely used mitigation…

Machine Learning · Computer Science 2026-04-03 Felix Stollenwerk , Anna Lokrantz , Niclas Hertzberg

There remain many open questions pertaining to the scaling behaviour of Transformer architectures. These scaling decisions and findings can be critical, as training runs often come with an associated computational cost which have both…

Computation and Language · Computer Science 2022-02-01 Yi Tay , Mostafa Dehghani , Jinfeng Rao , William Fedus , Samira Abnar , Hyung Won Chung , Sharan Narang , Dani Yogatama , Ashish Vaswani , Donald Metzler

Learning rate schedule has a major impact on the performance of deep learning models. Still, the choice of a schedule is often heuristical. We aim to develop a precise understanding of the effects of different learning rate schedules and…

Machine Learning · Computer Science 2020-02-25 Guillaume Leclerc , Aleksander Madry

The same machine learning model running on different edge devices may produce highly-divergent outputs on a nearly-identical input. Possible reasons for the divergence include differences in the device sensors, the device's signal…

Machine Learning · Computer Science 2020-10-20 Eyal Cidon , Evgenya Pergament , Zain Asgar , Asaf Cidon , Sachin Katti

We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the possibly unstable open-loop matrix by employing properly…

Machine Learning · Statistics 2025-09-30 Reza Sadeghi Hafshejani , Mohamad Kazem Shirani Fradonbeh

Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training…

Computation and Language · Computer Science 2023-05-09 Yangyi Chen , Lifan Yuan , Ganqu Cui , Zhiyuan Liu , Heng Ji

In scalable machine learning systems, model training is often parallelized over multiple nodes that run without tight synchronization. Most analysis results for the related asynchronous algorithms use an upper bound on the information…

Machine Learning · Computer Science 2022-04-12 Xuyang Wu , Sindri Magnusson , Hamid Reza Feyzmahdavian , Mikael Johansson

Most machine learning techniques are based upon statistical learning theory, often simplified for the sake of computing speed. This paper is focused on the uncertainty aspect of mathematical modeling in machine learning. Regression analysis…

Machine Learning · Computer Science 2022-06-07 Valentin Arkov

Recent work has shown that Transformers can perform in-context learning for linear regression under restrictive assumptions, including i.i.d. data, Gaussian noise, and Gaussian regression coefficients. However, real-world data often violate…

Machine Learning · Computer Science 2026-03-20 Hoang T. H. Cao , Hai D. V. Trinh , Tho Quan , Lan V. Truong

As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical instability has emerged as a critical reliability issue. While recent studies have demonstrated the…

Artificial Intelligence · Computer Science 2026-04-16 Chashi Mahiul Islam , Alan Villarreal , Mao Nishino , Shaeke Salman , Xiuwen Liu

Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets. This provides an efficient way for practitioners and researchers alike to compare…

Machine Learning · Computer Science 2025-06-04 Leshem Choshen , Yang Zhang , Jacob Andreas

This work focuses on the training dynamics of one associative memory module storing outer products of token embeddings. We reduce this problem to the study of a system of particles, which interact according to properties of the data…

Machine Learning · Computer Science 2024-03-01 Vivien Cabannes , Berfin Simsek , Alberto Bietti

Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the DNN's predictions become more erroneous over time, resulting…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Md Yousuf Harun , Christopher Kanan

Large batch size training of Neural Networks has been shown to incur accuracy loss when trained with the current methods. The exact underlying reasons for this are still not completely understood. Here, we study large batch size training…

Computer Vision and Pattern Recognition · Computer Science 2021-04-21 Zhewei Yao , Amir Gholami , Qi Lei , Kurt Keutzer , Michael W. Mahoney

This paper uses the notion of algorithmic stability to derive novel generalization bounds for several families of transductive regression algorithms, both by using convexity and closed-form solutions. Our analysis helps compare the…

Machine Learning · Computer Science 2009-04-07 Corinna Cortes , Mehryar Mohri , Dmitry Pechyony , Ashish Rastogi

Recent large language models have been trained on vast datasets, but also often on repeated data, either intentionally for the purpose of upweighting higher quality data, or unintentionally because data deduplication is not perfect and the…

Reinforcement learning methods often produce brittle policies -- policies that perform well during training, but generalize poorly beyond their direct training experience, thus becoming unstable under small disturbances. To address this…

Robotics · Computer Science 2023-02-14 Sergey Pankov

Inference in large-scale AI models is typically performed on dense parameter matrices, leading to inference cost and system complexity that scale unsustainably with model size. This limitation does not arise from insufficient model…

Machine Learning · Computer Science 2026-03-17 Jidong Jin