English
Related papers

Related papers: Self-Supervised Inference in State-Space Models

200 papers

We consider approximate maximum likelihood parameter estimation in nonlinear state-space models. We discuss both direct optimization of the likelihood and expectation--maximization (EM). For EM, we also give closed-form expressions for the…

Methodology · Statistics 2015-11-03 Juho Kokkala , Arno Solin , Simo Särkkä

Mechanistic models with differential equations are a key component of scientific applications of machine learning. Inference in such models is usually computationally demanding, because it involves repeatedly solving the differential…

Machine Learning · Statistics 2022-07-06 Jonathan Schmidt , Nicholas Krämer , Philipp Hennig

Recurrent neural networks (RNNs) are nonlinear dynamical models commonly used in the machine learning and dynamical systems literature to represent complex dynamical or sequential relationships between variables. More recently, as deep…

Methodology · Statistics 2018-02-08 Patrick L. McDermott , Christopher K. Wikle

We present an R package bssm for Bayesian non-linear/non-Gaussian state space modelling. Unlike the existing packages, bssm allows for easy-to-use approximate inference based on Gaussian approximations such as the Laplace approximation and…

Computation · Statistics 2022-04-13 Jouni Helske , Matti Vihola

In this paper we present a fully Bayesian latent variable model which exploits conditional nonlinear(in)-dependence structures to learn an efficient latent representation. The latent space is factorized to represent shared and private…

Machine Learning · Computer Science 2012-06-22 Andreas Damianou , Carl Ek , Michalis Titsias , Neil Lawrence

This work presents an approach for incrementally updating deep neural network (DNN) models in a non-stationary environment. DNN models are sensitive to changes in input data distribution, which limits their application to problem settings…

Machine Learning · Computer Science 2023-01-31 Abhinit Kumar Ambastha , Leong Tze Yun

In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Mehdi Noroozi , Ananth Vinjimoor , Paolo Favaro , Hamed Pirsiavash

This work presents a data-driven method for learning low-dimensional time-dependent physics-based surrogate models whose predictions are endowed with uncertainty estimates. We use the operator inference approach to model reduction that…

Numerical Analysis · Mathematics 2025-03-19 Shane A. McQuarrie , Anirban Chaudhuri , Karen E. Willcox , Mengwu Guo

We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the…

Machine Learning · Statistics 2019-10-15 Adnan Akhundov , Maximilian Soelch , Justin Bayer , Patrick van der Smagt

In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…

Artificial Intelligence · Computer Science 2016-09-20 Russell Stewart , Stefano Ermon

Practitioners often face the challenge of deploying prediction models in new environments with shifted distributions of covariates and responses. With observational data, such shifts are often driven by unobserved confounding, and can in…

Machine Learning · Computer Science 2026-04-02 Kulunu Dharmakeerthi , YoonHaeng Hur , Tengyuan Liang

One of the most surprising and exciting discoveries in supervised learning was the benefit of overparameterization (i.e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical…

Machine Learning · Statistics 2020-07-17 Rares-Darius Buhai , Yoni Halpern , Yoon Kim , Andrej Risteski , David Sontag

Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data to learn useful semantic representations. These pretext tasks are created solely using the input features,…

Machine Learning · Computer Science 2021-11-16 Jason D. Lee , Qi Lei , Nikunj Saunshi , Jiacheng Zhuo

We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Alexandre Boulch , Corentin Sautier , Björn Michele , Gilles Puy , Renaud Marlet

The supervised training of high-capacity models on large datasets containing hundreds of thousands of document-summary pairs is critical to the recent success of deep learning techniques for abstractive summarization. Unfortunately, in most…

Computation and Language · Computer Science 2020-04-22 Reinald Kim Amplayo , Mirella Lapata

We introduce Variational State-Space Filters (VSSF), a new method for unsupervised learning, identification, and filtering of latent Markov state space models from raw pixels. We present a theoretically sound framework for latent state…

Machine Learning · Computer Science 2022-03-22 Daniel Pfrommer , Nikolai Matni

Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximization achieve this surprising feat, even matching golden finetuning performance. Yet why they work…

Machine Learning · Computer Science 2026-01-21 Tianyi Qiu , Ahmed Hani Ismail , Zhonghao He , Shi Feng

We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes…

Computation and Language · Computer Science 2022-09-20 Takashi Wada , Timothy Baldwin , Yuji Matsumoto , Jey Han Lau

This paper offers a qualitative insight into the convergence of Bayesian parameter inference in a setup which mimics the modeling of the spread of a disease with associated disease measurements. Specifically, we are interested in the…

Statistics Theory · Mathematics 2022-12-08 Samuel Bronstein , Stefan Engblom , Robin Marin

We develop latent variable models for Bayesian learning based low-rank matrix completion and reconstruction from linear measurements. For under-determined systems, the developed methods are shown to reconstruct low-rank matrices when…

Machine Learning · Statistics 2015-01-26 Martin Sundin , Cristian R. Rojas , Magnus Jansson , Saikat Chatterjee