Search Results for author:
Found 92 papers, 49 papers with code
Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models
Though diffusion models have been successfully applied to various image restoration (IR) tasks, their performance is sensitive to the choice of training datasets.
On the equivalence of direct and indirect data-driven predictive control approaches
Recently, several direct Data-Driven Predictive Control (DDPC) methods have been proposed, advocating the possibility of designing predictive controllers from historical input-output trajectories without the need to identify a model.
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
We show that such an SDE has a solution that we can use to calculate the log probability of the policy, yielding an entropy regularizer that improves the exploration of offline datasets.
Safe reinforcement learning in uncertain contexts
In this work, we drop this assumption and show how we can perform safe learning when we cannot directly measure the context variables.
Structured state-space models are deep Wiener models
The goal of this paper is to provide a system identification-friendly introduction to the Structured State-space Models (SSMs).
On Feynman--Kac training of partial Bayesian neural networks
Recently, partial Bayesian neural networks (pBNNs), which only consider a subset of the parameters to be stochastic, were shown to perform competitively with full Bayesian neural networks.
Non-ergodicity in reinforcement learning: robustness via ergodicity transformations
The expected value is the average over the statistical ensemble of infinitely many trajectories.
Regularization properties of adversarially-trained linear regression
And, conversely, the minimum-norm interpolator is the solution to adversarial training with a given radius.
Controlling Vision-Language Models for Multi-Task Image Restoration
In this paper, we present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks as a multi-task framework for image restoration.
Ranked #1 on
Single Image Deraining
on Rain100H
End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks
Background: Atrial fibrillation (AF) is one of the most common cardiac arrhythmias that affects millions of people each year worldwide and it is closely linked to increased risk of cardiovascular diseases such as stroke and heart failure.
Lens-to-lens bokeh effect transformation. NTIRE 2023 challenge report
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models
This work aims to improve the applicability of diffusion models in realistic image restoration.
On the trade-off between event-based and periodic state estimation under bandwidth constraints
In this article, we discuss, for a specific example, when the additional complexity of event-based methods is beneficial.
Invertible Kernel PCA with Random Fourier Features
Kernel principal component analysis (kPCA) is a widely studied method to construct a low-dimensional data representation after a nonlinear transformation.
How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?
We then employ our benchmark to evaluate many of the most common uncertainty estimation methods, as well as two state-of-the-art uncertainty scores from the task of out-of-distribution detection.
Deep networks for system identification: a Survey
For this reason, we provide a survey of deep learning from a system identification perspective.
Image Restoration with Mean-Reverting Stochastic Differential Equations
This paper presents a stochastic differential equation (SDE) approach for general-purpose image restoration.
Ranked #2 on
Single Image Deraining
on Rain100H
ECG-Based Electrolyte Prediction: Evaluating Regression and Probabilistic Methods
We therefore investigate if regression methods can be used for accurate ECG-based prediction of electrolyte concentrations.
Surprises in adversarially-trained linear regression
We prove that adversarial training with small disturbances gives the solution with the minimum-norm that interpolates the training data.
Probabilistic Estimation of Instantaneous Frequencies of Chirp Signals
We present a continuous-time probabilistic approach for estimating the chirp signal and its instantaneous frequency function when the true forms of these functions are not accessible.
Overparameterized Linear Regression under Adversarial Attacks
This fact is then exploited to establish similarities between adversarial training and parameter-shrinking methods and to study how the training might affect the robustness of the estimated models.
Incorporating Sum Constraints into Multitask Gaussian Processes
Machine learning models can be improved by adapting them to respect existing background knowledge.
Efficient Learning of the Parameters of Non-Linear Models using Differentiable Resampling in Particle Filters
It has been widely documented that the sampling and resampling steps in particle filters cannot be differentiated.
Learning Proposals for Practical Energy-Based Regression
Energy-based models (EBMs) have experienced a resurgence within machine learning in recent years, including as a promising alternative for probabilistic regression.
Learning deep autoregressive models for hierarchical data
We propose a model for hierarchical structured data as an extension to the stochastic temporal convolutional network.
Unsupervised dynamic modeling of medical image transformation
For this, we use a conditional variational auto-encoder (CVAE) to nonlinearly map the higher-dimensional image to a lower-dimensional space, wherein we model the dynamics with a linear Gaussian state-space model (LG-SSM).
How Convolutional Neural Networks Deal with Aliasing
The convolutional neural network (CNN) remains an essential tool in solving computer vision problems.
Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics
It is typically observed that the model validation performance follows a U-shaped curve as the model complexity increases.
Accurate 3D Object Detection using Energy-Based Models
On the KITTI dataset, our proposed approach consistently outperforms the SA-SSD baseline across all 3DOD metrics, demonstrating the potential of EBM-based regression for highly accurate 3DOD.
Ranked #1 on
3D Object Detection
on KITTI Cars Easy val
Deep Energy-Based NARX Models
This paper is directed towards the problem of learning nonlinear ARX models based on system input--output data.
How to Train Your Energy-Based Model for Regression
While they are commonly employed for generative image modeling, recent work has applied EBMs also for regression tasks, achieving state-of-the-art performance on object detection and visual tracking.
Ranked #1 on
Visual Object Tracking
on OTB-100
Deep State Space Models for Nonlinear System Identification
Deep state space models (SSMs) are an actively researched model class for temporal models developed in the deep learning community which have a close connection to classic SSMs.
Registration by tracking for sequential 2D MRI
Together with a sparse-to-dense interpolation scheme we can then estimate of the displacement field.
Gaussian Variational State Estimation for Nonlinear State-Space Models
In this paper, the problem of state estimation, in the context of both filtering and smoothing, for nonlinear state-space models is considered.
Particle filter with rejection control and unbiased estimator of the marginal likelihood
While the variance reducing properties of rejection control are known, there has not been (to the best of our knowledge) any work on unbiased estimation of the marginal likelihood (also known as the model evidence or the normalizing constant) in this type of particle filter.
Energy-Based Models for Deep Probabilistic Regression
In our proposed approach, we create an energy-based model of the conditional target density p(y|x), using a deep neural network to predict the un-normalized density from (x, y).
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric)
Deep kernel learning for integral measurements
Deep kernel learning refers to a Gaussian process that incorporates neural networks to improve the modelling of complex functions.
Deep Convolutional Networks in System Identification
Recent developments within deep learning are relevant for nonlinear system identification problems.
Probabilistic programming for birth-death models of evolution using an alive particle filter with delayed sampling
Probabilistic programming languages (PPLs) give phylogeneticists a new and exciting tool: their models can be implemented as probabilistic programs with just a basic knowledge of programming.
Beyond exploding and vanishing gradients: analysing RNN training using attractors and smoothness
The exploding and vanishing gradient problem has been the major conceptual principle behind most architecture and training improvements in recurrent neural networks (RNNs) during the last decade.
Robust exploration in linear quadratic reinforcement learning
This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function.
Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision
We therefore accept this task and propose a comprehensive evaluation framework for scalable epistemic uncertainty estimation methods in deep learning.
On the smoothness of nonlinear system identification
We shed new light on the \textit{smoothness} of optimization problems arising in prediction error parameter estimation of linear and nonlinear systems.
Automatic diagnosis of the 12-lead ECG using a deep neural network
The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models.
Elements of Sequential Monte Carlo
A core problem in statistics and probabilistic machine learning is to compute probability distributions and expectations.
Nonlinear input design as optimal control of a Hamiltonian system
We propose an input design method for a general class of parametric probabilistic models, including nonlinear dynamical systems with process noise.
Evaluating model calibration in classification
Probabilistic classifiers output a probability distribution on target classes rather than just a class prediction.
Constructing the Matrix Multilayer Perceptron and its Application to the VAE
However, in certain scenarios we are interested in learning structured parameters (predictions) in the form of symmetric positive definite matrices.
Inferring Heterogeneous Causal Effects in Presence of Spatial Confounding
We address the problem of inferring the causal effect of an exposure on an outcome across space, using observational data.
Automatic Diagnosis of Short-Duration 12-Lead ECG using a Deep Convolutional Network
We present a model for predicting electrocardiogram (ECG) abnormalities in short-duration 12-lead ECG signals which outperformed medical doctors on the 4th year of their cardiology residency.
Reliable Semi-Supervised Learning when Labels are Missing at Random
Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data.
Automated learning with a probabilistic programming language: Birch
We introduce a formal description of models expressed as programs, and discuss some of the ways in which probabilistic programming languages can reveal the structure and form of these, in order to tailor inference methods.
Probabilistic approach to limited-data computed tomography reconstruction
The approach also allows for reformulation of come classical regularization methods as Laplacian and Tikhonov regularization as Gaussian process regression, and hence provides an efficient algorithm and principled means for their parameter tuning.
Data Consistency Approach to Model Validation
The contribution in this paper is a general criterion to evaluate the consistency of a set of statistical models with respect to observed data.
Learning convex bounds for linear quadratic control policy synthesis
Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance.
Conditionally Independent Multiresolution Gaussian Processes
This in turn results in models which are prone to overfitting in the sense of excessive sensitivity to the chosen resolution, and predictions which are non-smooth at the boundaries.
Learning Localized Spatio-Temporal Models From Streaming Data
We address the problem of predicting spatio-temporal processes with temporal patterns that vary across spatial regions, when data is obtained as a stream.
Data-Driven Impulse Response Regularization via Deep Learning
We consider the problem of impulse response estimation of stable linear single-input single-output systems.
How consistent is my model with the data? Information-Theoretic Model Check
The choice of model class is fundamental in statistical learning and system identification, no matter whether the class is derived from physical principles or is a generic black-box.
Delayed Sampling and Automatic Rao-Blackwellization of Probabilistic Programs
For inference with Sequential Monte Carlo, this automatically yields improvements such as locally-optimal proposals and Rao-Blackwellization.
Using Inertial Sensors for Position and Orientation Estimation
In this tutorial we focus on the signal processing aspects of position and orientation estimation using inertial sensors.
Robotics Systems and Control
On the construction of probabilistic Newton-type algorithms
It has recently been shown that many of the existing quasi-Newton algorithms can be formulated as learning algorithms, capable of learning local models of the cost functions.
Online Learning for Distribution-Free Prediction
We develop an online learning method for prediction, which is important in problems with large and/or streaming data sets.
Probabilistic learning of nonlinear dynamical systems using sequential Monte Carlo
We are concerned with the problem of learning probabilistic models of dynamical systems from measured data.
Linearly constrained Gaussian processes
We consider a modification of the covariance function in Gaussian processes to correctly account for known linear constraints.
Learning of state-space models with highly informative observations: a tempered Sequential Monte Carlo solution
In particular, for learning of unknown parameters in nonlinear state-space models, methods based on the particle filter (a Monte Carlo method) have proven very useful.
Smoothing with Couplings of Conditional Particle Filters
The method combines two recent breakthroughs: the first is a generic debiasing technique for Markov chains due to Rhee and Glynn, and the second is the introduction of a uniformly ergodic Markov chain for smoothing, the conditional particle filter of Andrieu, Doucet and Holenstein.
Methodology Computation
High-dimensional Filtering using Nested Sequential Monte Carlo
Sequential Monte Carlo (SMC) methods comprise one of the most successful approaches to approximate Bayesian filtering.
Prediction performance after learning in Gaussian process regression
Starting from a generalization of the Cram\'er-Rao bound, we derive a more accurate MSE bound which provides a measure of uncertainty for prediction of Gaussian processes.
A sequential Monte Carlo approach to Thompson sampling for Bayesian optimization
This recommendation is usually selected by optimizing a given acquisition function.
A flexible state space model for learning nonlinear dynamical systems
We consider a nonlinear state-space model with the state transition and observation functions expressed as basis function expansions.
System Identification through Online Sparse Gaussian Process Regression with Input Noise
There has been a growing interest in using non-parametric regression methods like Gaussian Process (GP) regression for system identification.
Accelerating pseudo-marginal Metropolis-Hastings by correlating auxiliary variables
Pseudo-marginal Metropolis-Hastings (pmMH) is a powerful method for Bayesian inference in models where the posterior distribution is analytical intractable or computationally costly to evaluate directly.
Getting Started with Particle Metropolis-Hastings for Inference in Nonlinear Dynamical Models
This tutorial provides a gentle introduction to the particle Metropolis-Hastings (PMH) algorithm for parameter inference in nonlinear state-space models together with a software implementation in the statistical programming language R. We employ a step-by-step approach to develop an implementation of the PMH algorithm (and the particle filter within) together with the reader.
Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models
We consider a particularly important instance of this challenge, the pixels-to-torques problem, where an RL agent learns a closed-loop control policy ("torques") from pixel information only.
Model-based Reinforcement Learning
Model Predictive Control
+2
Modeling and interpolation of the ambient magnetic field by Gaussian processes
Anomalies in the ambient magnetic field can be used as features in indoor positioning and navigation.
Bayesian optimisation for fast approximate inference in state-space models with intractable likelihoods
We consider the problem of approximate Bayesian parameter inference in non-linear state-space models with intractable likelihoods.
Computationally Efficient Bayesian Learning of Gaussian Process State Space Models
We present a procedure for efficient Bayesian learning in Gaussian process state space models, where the representation is formed by projecting the problem onto a set of approximate eigenfunctions derived from the prior covariance structure.
Sequential Monte Carlo Methods for System Identification
One of the key challenges in identifying nonlinear and possibly non-Gaussian state space models (SSMs) is the intractability of estimating the system state.
Quasi-Newton particle Metropolis-Hastings
A possible application is parameter inference in the challenging class of SSMs with intractable likelihoods.
Newton-based maximum likelihood estimation in nonlinear state space models
Maximum likelihood (ML) estimation using Newton's method in nonlinear state space models (SSMs) is a challenging problem due to the analytical intractability of the log-likelihood and its gradient and Hessian.
Nested Sequential Monte Carlo Methods
NSMC generalises the SMC framework by requiring only approximate, properly weighted, samples from the SMC proposal distribution, while still resulting in a correct SMC algorithm.
From Pixels to Torques: Policy Learning with Deep Dynamical Models
In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel information only.
Model-based Reinforcement Learning
Model Predictive Control
+2
Marginalizing Gaussian Process Hyperparameters using Sequential Monte Carlo
Gaussian process regression is a popular method for non-parametric probabilistic modeling of functions.
Learning deep dynamical models from image pixels
In particular, we jointly learn a low-dimensional embedding of the observation by means of deep auto-encoders and a predictive transition model in this low-dimensional space.
Identification of jump Markov linear models using particle filters
Jump Markov linear models consists of a finite number of linear state space models and a discrete variable encoding the jumps (or switches) between the different linear models.
Divide-and-Conquer with Sequential Monte Carlo
We propose a novel class of Sequential Monte Carlo (SMC) algorithms, appropriate for inference in probabilistic graphical models.
Sequential Monte Carlo for Graphical Models
We propose a new framework for how to use sequential Monte Carlo (SMC) algorithms for inference in probabilistic graphical models (PGM).
Particle Gibbs with Ancestor Sampling
Particle Markov chain Monte Carlo (PMCMC) is a systematic way of combining the two main tools used for Monte Carlo statistical inference: sequential Monte Carlo (SMC) and Markov chain Monte Carlo (MCMC).
Identification of Gaussian Process State-Space Models with Particle Stochastic Approximation EM
Gaussian process state-space models (GP-SSMs) are a very flexible family of models of nonlinear dynamical systems.
Particle Metropolis-Hastings using gradient and Hessian information
Particle Metropolis-Hastings (PMH) allows for Bayesian parameter inference in nonlinear state space models by combining Markov chain Monte Carlo (MCMC) and particle filtering.
Bayesian Inference and Learning in Gaussian Process State-Space Models with Particle MCMC
State-space models are successfully used in many areas of science, engineering and economics to model time series and dynamical systems.
