English
Related papers

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

200 papers

Time series modeling is a well-established problem, which often requires that methods (1) expressively represent complicated dependencies, (2) forecast long horizons, and (3) efficiently train over long sequences. State-space models (SSMs)…

Machine Learning · Computer Science 2023-03-17 Michael Zhang , Khaled K. Saab , Michael Poli , Tri Dao , Karan Goel , Christopher Ré

State-space models (SSMs) have recently attention as an efficient alternative to computationally expensive attention-based models for sequence modeling. They rely on linear recurrences to integrate information over time, enabling fast…

Machine Learning · Computer Science 2026-01-01 Mahdi Karami , Ali Behrouz , Peilin Zhong , Razvan Pascanu , Vahab Mirrokni

Recurrent Neural Networks (RNNs) can be seriously impacted by the initial parameters assignment, which may result in poor generalization performances on new unseen data. With the objective to tackle this crucial issue, in the context of RNN…

Machine Learning · Computer Science 2019-11-05 Dino Ienco , Roberto Interdonato , Raffaele Gaetano

Accurately predicting industrial aging processes makes it possible to schedule maintenance events further in advance, ensuring a cost-efficient and reliable operation of the plant. So far, these degradation processes were usually described…

Machine Learning · Computer Science 2020-10-22 Mihail Bogojeski , Simeon Sauer , Franziska Horn , Klaus-Robert Müller

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the…

Machine Learning · Computer Science 2020-03-05 Leslie Rice , Eric Wong , J. Zico Kolter

Although state-space models (SSMs) have demonstrated strong performance on long-sequence benchmarks, most research has emphasized predictive accuracy rather than interpretability. In this work, we present the first systematic kernel…

Machine Learning · Computer Science 2026-01-21 Srividya Ravikumar , Abhinav Anand , Shweta Verma , Mira Mezini

Processing long temporal sequences is a key challenge in deep learning. In recent years, Transformers have become state-of-the-art for this task, but suffer from excessive memory requirements due to the need to explicitly store the…

Machine Learning · Computer Science 2025-07-09 Sebastian Siegel , Ming-Jay Yang , John-Paul Strachan

While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs continues to be a significant challenge. One such task is long input summarization, where inputs are…

Computation and Language · Computer Science 2022-08-10 Jason Phang , Yao Zhao , Peter J. Liu

Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in…

Machine Learning · Statistics 2019-03-01 Adarsh Subbaswamy , Peter Schulam , Suchi Saria

In many applications, one works with neural network models trained by someone else. For such pretrained models, one may not have access to training data or test data. Moreover, one may not know details about the model, e.g., the specifics…

Machine Learning · Computer Science 2021-09-15 Charles H. Martin , Tongsu , Peng , Michael W. Mahoney

This paper provides a starting point for Software Engineering (SE) researchers and practitioners faced with the problem of training machine learning models on small datasets. Due to the high costs associated with labeling data, in Software…

Software Engineering · Computer Science 2021-06-30 Julian Aron Prenner , Romain Robbes

Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as "memory" for the trained models and help them generalize well on unseen data. However, in absence of training data, the utility of a…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Gaurav Kumar Nayak , Konda Reddy Mopuri , Saksham Jain , Anirban Chakraborty

Pretraining a neural network on a large dataset is becoming a cornerstone in machine learning that is within the reach of only a few communities with large-resources. We aim at an ambitious goal of democratizing pretraining. Towards that…

Machine Learning · Computer Science 2023-06-01 Boris Knyazev , Doha Hwang , Simon Lacoste-Julien

Our goal is to enable machine learning systems to be trained interactively. This requires models that perform well and train quickly, without large amounts of hand-labeled data. We take a step forward in this direction by borrowing from…

In this study, we delve into the Structured State Space Model (S4), Change Point Detection methodologies, and the Switching Non-linear Dynamics System (SNLDS). Our central proposition is an enhanced inference technique and long-range…

Machine Learning · Computer Science 2024-07-30 Jiaming Zhang , Yang Ding , Yunfeng Gao

We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts…

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the…

Machine Learning · Computer Science 2025-05-29 Zachary Shinnick , Liangze Jiang , Hemanth Saratchandran , Anton van den Hengel , Damien Teney

Various deep learning models, especially some latest Transformer-based approaches, have greatly improved the state-of-art performance for long-term time series forecasting.However, those transformer-based models suffer a severe…

Machine Learning · Computer Science 2022-06-27 Tian Zhou , Jianqing Zhu , Xue Wang , Ziqing Ma , Qingsong Wen , Liang Sun , Rong Jin

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Recurrent Neural Networks (RNNs) laid the foundation for sequence modeling, but their intrinsic sequential nature restricts parallel computation, creating a fundamental barrier to scaling. This has led to the dominance of parallelizable…

Machine Learning · Computer Science 2025-11-04 Federico Danieli , Pau Rodriguez , Miguel Sarabia , Xavier Suau , Luca Zappella
‹ Prev 1 8 9 10 Next ›