English
Related papers

Related papers: Learning Recurrent Models with Temporally Local Ru…

200 papers

We are interested in how to design reinforcement learning agents that provably reduce the sample complexity for learning new tasks by transferring knowledge from previously-solved ones. The availability of solutions to related problems…

Machine Learning · Computer Science 2020-07-03 Andrea Tirinzoni , Riccardo Poiani , Marcello Restelli

Ensemble weather forecasts based on multiple runs of numerical weather prediction models typically show systematic errors and require post-processing to obtain reliable forecasts. Accurately modeling multivariate dependencies is crucial in…

Atmospheric and Oceanic Physics · Physics 2024-02-02 Jieyu Chen , Tim Janke , Florian Steinke , Sebastian Lerch

Sequential computation via autoregressive generation can make difficult tasks learnable, but the generation order of intermediate states strongly affects whether training succeeds. We address the problem of discovering a learning-friendly…

Machine Learning · Computer Science 2026-05-11 Yuta Sato , Kazuhiko Kawamoto , Hiroshi Kera

Recurrent Neural Networks (RNNs) are widely used for sequential processing but face fundamental limitations with continual inference due to state saturation, requiring disruptive hidden state resets. However, reset-based methods impose…

Machine Learning · Computer Science 2024-12-23 Bojian Yin , Federico Corradi

We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a…

Machine Learning · Statistics 2014-06-02 Danilo Jimenez Rezende , Shakir Mohamed , Daan Wierstra

Recurrent neural networks with a gating mechanism such as an LSTM or GRU are powerful tools to model sequential data. In the mechanism, a forget gate, which was introduced to control information flow in a hidden state in the RNN, has…

Machine Learning · Statistics 2021-11-08 Kentaro Ohno , Atsutoshi Kumagai

Beyond their origin in modeling many-body quantum systems, tensor networks have emerged as a promising class of models for solving machine learning problems, notably in unsupervised generative learning. While possessing many desirable…

Machine Learning · Computer Science 2024-07-26 Alex Meiburg , Jing Chen , Jacob Miller , Raphaëlle Tihon , Guillaume Rabusseau , Alejandro Perdomo-Ortiz

It is well known that deep generative models have a rich latent space, and that it is possible to smoothly manipulate their outputs by traversing this latent space. Recently, architectures have emerged that allow for more complex…

Machine Learning · Computer Science 2019-12-06 Andrew Gambardella , Atılım Güneş Baydin , Philip H. S. Torr

Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solution of systems of…

Neural and Evolutionary Computing · Computer Science 2019-11-18 Dylan Richard Muir

Learning behavioral patterns from observational data has been a de-facto approach to motion forecasting. Yet, the current paradigm suffers from two shortcomings: brittle under distribution shifts and inefficient for knowledge transfer. In…

Machine Learning · Computer Science 2022-04-06 Yuejiang Liu , Riccardo Cadei , Jonas Schweizer , Sherwin Bahmani , Alexandre Alahi

In this work, we propose to learn a generative model using both learned features (through a latent space) and memories (through neighbors). Although human learning makes seamless use of both learned perceptual features and instance recall,…

Machine Learning · Statistics 2019-11-21 Yang Li , Tianxiang Gao , Junier B. Oliva

We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are…

Machine Learning · Computer Science 2018-12-12 Hugo Caselles-Dupré , Michael Garcia-Ortiz , David Filliat

Temporal point processes are powerful generative models for event sequences that capture complex dependencies in time-series data. They are commonly specified using autoregressive models that learn the distribution of the next event from…

Machine Learning · Computer Science 2025-10-24 Marin Biloš , Anderson Schneider , Yuriy Nevmyvaka

We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative…

Machine Learning · Computer Science 2015-02-11 Yujia Li , Kevin Swersky , Richard Zemel

Deep generative models such as diffusion and flow matching are powerful machine learning tools capable of learning and sampling from high-dimensional distributions. They are particularly useful when the training data appears to be…

High Energy Physics - Phenomenology · Physics 2026-04-30 Zachary Bogorad , Ibrahim Elsharkawy , Yonatan Kahn , Andrew J. Larkoski , Noam Levi

Temporal gates play a significant role in modern recurrent-based neural encoders, enabling fine-grained control over recursive compositional operations over time. In recurrent models such as the long short-term memory (LSTM), temporal gates…

Computation and Language · Computer Science 2017-11-22 Yi Tay , Luu Anh Tuan , Siu Cheung Hui

After learning a concept, humans are also able to continually generalize their learned concepts to new domains by observing only a few labeled instances without any interference with the past learned knowledge. In contrast, learning…

Machine Learning · Computer Science 2019-09-10 Mohammad Rostami , Soheil Kolouri , James McClelland , Praveen Pilly

We introduce a neural network architecture that logarithmically reduces the number of self-rehearsal steps in the generative rehearsal of continually learned models. In continual learning (CL), training samples come in subsequent tasks, and…

Machine Learning · Computer Science 2022-01-19 Wojciech Masarczyk , Paweł Wawrzyński , Daniel Marczak , Kamil Deja , Tomasz Trzciński

Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…

Machine Learning · Computer Science 2018-10-26 Matthew MacKay , Paul Vicol , Jimmy Ba , Roger Grosse

Behavior cloning of expert demonstrations can speed up learning optimal policies in a more sample-efficient way over reinforcement learning. However, the policy cannot extrapolate well to unseen states outside of the demonstration data,…

Machine Learning · Computer Science 2022-10-19 Jung Yeon Park , Lawson L. S. Wong