paper-with-me

홈 › Papers

Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface

2021-07-04 · ICLR 2022 4 · Tuan Anh Le, Katherine M. Collins, Luke Hewitt, Kevin Ellis, N. Siddharth, Samuel J. Gershman, Joshua B. Tenenbaum

Modeling complex phenomena typically involves the use of both discrete and continuous variables. Such a setting applies across a wide range of problems, from identifying trends in time-series data to performing effective compositional scene understanding in images. Here, we propose Hybrid Memoised Wake-Sleep (HMWS), an algorithm for effective inference in such hybrid discrete-continuous models. Prior approaches to learning suffer as they need to perform repeated expensive inner-loop discrete inference. We build on a recent approach, Memoised Wake-Sleep (MWS), which alleviates part of the problem by memoising discrete variables, and extend it to allow for a principled and effective way to handle continuous variables by learning a separate recognition model used for importance-sampling based approximate inference and marginalization. We evaluate HMWS in the GP-kernel learning and 3D scene understanding domains, and show that it outperforms current state-of-the-art inference methods.

📄 PDF Abstract BibTeX arXiv:2107.06393

Code (0)

등록된 구현이 없습니다.

Tasks

Scene UnderstandingTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Learning to learn generative programs with Memoised Wake-Sleep

2020-07-06 · Luke B. Hewitt, Tuan Anh Le, Joshua B. Tenenbaum

We study a class of neuro-symbolic generative models in which neural networks are used both for inference and as priors over symbolic, data-generating programs. As generative models, these programs capture compositional …

Explainable ModelsFew-Shot LearningProgram induction

Reweighted Wake-Sleep

2014-06-11 · Jörg Bornschein, Yoshua Bengio

Training deep directed graphical models with many hidden variables and performing inference remains a major challenge. Helmholtz machines and deep belief networks are such models, and the wake-sleep algorithm has been pr…

Explaining and Generalizing Back-Translation through Wake-Sleep

2018-06-12 · Ryan Cotterell, Julia Kreutzer

Back-translation has become a commonly employed heuristic for semi-supervised neural machine translation. The technique is both straightforward to apply and has led to state-of-the-art results. In this work, we offer a p…

Machine TranslationTranslation

Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference

2026-05-25 · Sangyun Lee, Sean McLeish, Tom Goldstein, Giulia Fanti arxiv

Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in…

A robust generalizable device-agnostic deep learning model for sleep-wake determination from triaxial wrist accelerometry

2025-12-01 · Nasim Montazeri, Stone Yang, Dominik Luszczynski, John Zhang 외 arxiv

Study Objectives: Wrist accelerometry is widely used for inferring sleep-wake state. Previous works demonstrated poor wake detection, without cross-device generalizability and validation in different age range and sleep …