English
Related papers

Related papers: Online learning of long-range dependencies

200 papers

Reinforcement learning (RL) agents performing complex tasks must be able to remember observations and actions across sizable time intervals. This is especially true during the initial learning stages, when exploratory behaviour can increase…

Machine Learning · Computer Science 2018-05-15 Thomas Stepleton , Razvan Pascanu , Will Dabney , Siddhant M. Jayakumar , Hubert Soyer , Remi Munos

We present a framework for compactly summarizing many recent results in efficient and/or biologically plausible online training of recurrent neural networks (RNN). The framework organizes algorithms according to several criteria: (a) past…

Machine Learning · Computer Science 2019-07-08 Owen Marschall , Kyunghyun Cho , Cristina Savin

Learning to act in an environment to maximise rewards is among the brain's key functions. This process has often been conceptualised within the framework of reinforcement learning, which has also gained prominence in machine learning and…

Machine Learning · Computer Science 2021-09-22 Emma L. Roscow , Raymond Chua , Rui Ponte Costa , Matt W. Jones , Nathan Lepora

Maximizing long-term rewards is the primary goal in sequential decision-making problems. The majority of existing methods assume that side information is freely available, enabling the learning agent to observe all features' states before…

Machine Learning · Computer Science 2023-07-19 Saeed Ghoorchian , Evgenii Kortukov , Setareh Maghsudi

Online classification is a central problem in optimization, statistical learning and data science. Classical algorithms such as the perceptron offer efficient updates and finite mistake guarantees on linearly separable data, but they do not…

Optimization and Control · Mathematics 2025-09-25 Nam Ho-Nguyen , Fatma Kılınç-Karzan , Ellie Nguyen , Lingqing Shen

We propose a new model for augmenting algorithms with predictions by requiring that they are formally learnable and instance robust. Learnability ensures that predictions can be efficiently constructed from a reasonable amount of past data.…

Machine Learning · Computer Science 2021-07-05 Thomas Lavastida , Benjamin Moseley , R. Ravi , Chenyang Xu

We consider the problem of sequential prediction and provide tools to study the minimax value of the associated game. Classical statistical learning theory provides several useful complexity measures to study learning with i.i.d. data. Our…

Machine Learning · Computer Science 2014-08-13 Alexander Rakhlin , Karthik Sridharan , Ambuj Tewari

This paper considers an online reinforcement learning algorithm that leverages pre-collected data (passive memory) from the environment for online interaction. We show that using passive memory improves performance and further provide…

Machine Learning · Computer Science 2024-10-21 Anay Pattanaik , Lav R. Varshney

We formalize the problem of online learning-unlearning, where a model is updated sequentially in an online setting while accommodating unlearning requests between updates. After a data point is unlearned, all subsequent outputs must be…

Machine Learning · Computer Science 2025-05-14 Yaxi Hu , Bernhard Schölkopf , Amartya Sanyal

We investigate an extension of continuous online learning in recurrent neural network language models. The model keeps a separate vector representation of the current unit of text being processed and adaptively adjusts it after each…

Computation and Language · Computer Science 2017-03-07 Marek Rei

Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets. However, this setting poses unique challenges: embedded devices have…

Machine Learning · Computer Science 2022-07-18 Tyler L. Hayes , Christopher Kanan

Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning." Traditional gradient-based networks require a lot of data to learn, often through…

Machine Learning · Computer Science 2016-05-20 Adam Santoro , Sergey Bartunov , Matthew Botvinick , Daan Wierstra , Timothy Lillicrap

Recurrent neural networks have gained widespread use in modeling sequential data. Learning long-term dependencies using these models remains difficult though, due to exploding or vanishing gradients. In this paper, we draw connections…

Machine Learning · Statistics 2019-02-27 Bo Chang , Minmin Chen , Eldad Haber , Ed H. Chi

We develop an online learning method for prediction, which is important in problems with large and/or streaming data sets. We formulate the learning approach using a covariance-fitting methodology, and show that the resulting predictor has…

Machine Learning · Computer Science 2017-03-16 Dave Zachariah , Petre Stoica , Thomas B. Schön

Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallelization. In this…

Artificial Intelligence · Computer Science 2017-11-03 Shiyu Chang , Yang Zhang , Wei Han , Mo Yu , Xiaoxiao Guo , Wei Tan , Xiaodong Cui , Michael Witbrock , Mark Hasegawa-Johnson , Thomas S. Huang

Large Language Models (LLMs) have a natural role in answering complex queries about data streams, but the high computational cost of LLM inference makes them infeasible in many such tasks. We propose online cascade learning, the first…

Machine Learning · Computer Science 2024-06-19 Lunyiu Nie , Zhimin Ding , Erdong Hu , Christopher Jermaine , Swarat Chaudhuri

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…

Machine Learning · Computer Science 2020-07-01 Antonio Carta , Alessandro Sperduti , Davide Bacciu

Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often…

Machine Learning · Computer Science 2025-10-14 Christian Raymond , Qi Chen , Bing Xue , Mengjie Zhang

Deep Neural Networks (DNNs) are typically trained by backpropagation in a batch learning setting, which requires the entire training data to be made available prior to the learning task. This is not scalable for many real-world scenarios…

Machine Learning · Computer Science 2017-11-13 Doyen Sahoo , Quang Pham , Jing Lu , Steven C. H. Hoi

Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets. Expanding upon this accomplishment, there has been a…

Machine Learning · Computer Science 2024-11-11 Jaehyeon Son , Soochan Lee , Gunhee Kim