English
Related papers

Related papers: Never Train from Scratch: Fair Comparison of Long-…

200 papers

Symbolic regression algorithms search a space of mathematical expressions for formulas that explain given data. Transformer-based models have emerged as a promising, scalable approach shifting the expensive combinatorial search to a…

Machine Learning · Computer Science 2025-09-25 Henrik Voigt , Paul Kahlmeyer , Kai Lawonn , Michael Habeck , Joachim Giesen

Foundation models have achieved remarkable success across diverse machine-learning domains through large-scale pretraining on large, diverse datasets. However, pretraining on such datasets introduces significant challenges due to…

Machine Learning · Computer Science 2025-04-16 Peiliang Gong , Emadeldeen Eldele , Min Wu , Zhenghua Chen , Xiaoli Li , Daoqiang Zhang

Prior-data fitted networks (PFNs) were recently proposed as a new paradigm for machine learning. Instead of training the network to an observed training set, a fixed model is pre-trained offline on small, simulated training sets from a…

Machine Learning · Statistics 2023-05-19 Thomas Nagler

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…

Machine Learning · Computer Science 2018-06-07 Xuhong Li , Yves Grandvalet , Franck Davoine

Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently dominant models based on Transformer architecture suffers from…

Hardware Architecture · Computer Science 2026-03-24 Saptarshi Mitra , Rachid Karami , Haocheng Xu , Sitao Huang , Hyoukjun Kwon

Deep learning techniques have revolutionised medical imaging, improving diagnostic accuracy and enabling both more accurate and earlier disease detection. However, the relationship between pre-training strategies and downstream performance…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Felix Krones

Finetuning Pretrained Language Models (PLM) for IR has been de facto the standard practice since their breakthrough effectiveness few years ago. But, is this approach well understood? In this paper, we study the impact of the pretraining…

Information Retrieval · Computer Science 2023-01-26 Carlos Lassance , Hervé Déjean , Stéphane Clinchant

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

Machine Learning · Computer Science 2022-07-05 Oleksiy Ostapenko , Timothee Lesort , Pau Rodríguez , Md Rifat Arefin , Arthur Douillard , Irina Rish , Laurent Charlin

Continual pre-training has demonstrated significant potential in enhancing model performance, particularly in domain-specific scenarios. The most common approach for packing data before continual pre-training involves concatenating input…

Computation and Language · Computer Science 2025-05-30 Ruicheng Yin , Xuan Gao , Changze Lv , Xiaohua Wang , Xiaoqing Zheng , Xuanjing Huang

Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspective. In this work, we present the first formal analysis of…

Machine Learning · Computer Science 2026-02-20 Sofiane Ennadir , Tianze Wang , Oleg Smirnov , Sahar Asadi , Lele Cao

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and…

Machine Learning · Computer Science 2020-12-10 George Zerveas , Srideepika Jayaraman , Dhaval Patel , Anuradha Bhamidipaty , Carsten Eickhoff

Amos et al. (2024) showed that the accuracy of Transformer models in sequence classification can be significantly improved by first pretraining with a masked token prediction objective without external data or augmentation, a procedure…

Machine Learning · Computer Science 2026-05-21 Omar Coser , Loredana Zollo , Paolo Soda , Antonio Orvieto

For a number of years since its introduction to hydrology, recurrent neural networks like long short-term memory (LSTM) have proven remarkably difficult to surpass in terms of daily hydrograph metrics on known, comparable benchmarks.…

Machine Learning · Computer Science 2023-06-22 Jiangtao Liu , Yuchen Bian , Chaopeng Shen

Despite their growing popularity, data-driven models of real-world dynamical systems require lots of data. However, due to sensing limitations as well as privacy concerns, this data is not always available, especially in domains such as…

Machine Learning · Computer Science 2023-02-24 Hussain Kazmi , Pierre Pinson

Direct evaluation of LLMs on benchmarks can be misleading because comparatively strong performance may reflect task familiarity rather than capability. The train-before-test approach controls for task familiarity by giving each model…

Machine Learning · Computer Science 2026-03-16 Kun Wang , Reinhard Heckel

In the low-data regime, it is difficult to train good supervised models from scratch. Instead practitioners turn to pre-trained models, leveraging transfer learning. Ensembling is an empirically and theoretically appealing way to construct…

Machine Learning · Computer Science 2020-10-20 Basil Mustafa , Carlos Riquelme , Joan Puigcerver , André Susano Pinto , Daniel Keysers , Neil Houlsby

Recent years have seen an explosion of diverse general purpose pre-training methodologies for computer vision. However, the impact that these pre-training methodologies have on person identification tasks (re-id) remains under-explored. We…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Thomas M. Metz , Matthew Q. Hill , Alice J. O'Toole

Pretraining is a common technique in deep learning for increasing performance and reducing training time, with promising experimental results in deep reinforcement learning (RL). However, pretraining requires a relevant dataset for…

Machine Learning · Computer Science 2021-10-07 Saurav Kadavath , Samuel Paradis , Brian Yao

Multivariate time series forecasting focuses on predicting future values based on historical context. State-of-the-art sequence-to-sequence models rely on neural attention between timesteps, which allows for temporal learning but fails to…

Machine Learning · Computer Science 2023-03-21 Jake Grigsby , Zhe Wang , Nam Nguyen , Yanjun Qi

Pre-training has been a popular learning paradigm in deep learning era, especially in annotation-insufficient scenario. Better ImageNet pre-trained models have been demonstrated, from the perspective of architecture, by previous research to…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Andong Deng , Xingjian Li , Di Hu , Tianyang Wang , Haoyi Xiong , Chengzhong Xu