Hans-Andrea Loeliger


Last Name

Loeliger

First Name

Hans-Andrea

ORCID

0000-0001-7153-7145

Organisational unit

03568 - Loeliger, Hans-Andrea / Loeliger, Hans-Andrea

Filters

Reset filters

Search Results

Publications 1 - 10 of 21
  • Offset detection from GNSS time series data: comparing an (unsupervised) augmented Kalman filter approach and supervised machine learning methods
    Item type: Other Conference Item
    Hohensinn, Roland; Crocetti, Laura; Ren, Elizabeth; et al. (2023)
    AGU Fall Meeting Abstracts
  • Decoding Gabidulin Codes via Partial Inverses of Linearized Polynomials
    Item type: Conference Paper
    Yu, Jiun-Hung; Loeliger, Hans-Andrea (2019)
    2019 IEEE International Symposium on Information Theory (ISIT)
    We study Gabidulin codes from a partial-inverse perspective and obtain a key equation with a new converse, as well as a new interpolation formula. The resulting new algorithm is efficient and conceptually simple.
  • Smoothed-NUV Priors for Imaging
    Item type: Journal Article
    Ma, Boxiao; Zalmai, Nour; Loeliger, Hans-Andrea (2022)
    IEEE Transactions on Image Processing
    Variations of L1-regularization including, in particular, total variation regularization, have hugely improved computational imaging. However, sharper edges and fewer staircase artifacts can be achieved with convex-concave regularizers. We present a new class of such regularizers using normal priors with unknown variance (NUV), which include smoothed versions of the logarithm function and smoothed versions of L-p norms with p <= 1. All NUV priors allow variational representations that lead to efficient algorithms for image reconstruction by iterative reweighted descent. A preferred such algorithm is iterative reweighted coordinate descent, which has no parameters (in particular, no step size to control) and is empirically robust and efficient. The proposed priors and algorithms are demonstrated with applications to tomography. We also note that the proposed priors come with built-in edge detection, which is demonstrated by an application to image segmentation.
  • Why maximum-a-posteriori blind image deblurring works after all
    Item type: Conference Paper
    Marti, Gian; Ma, Boxiao; Loeliger, Hans-Andrea (2021)
    2021 29th European Signal Processing Conference (EUSIPCO)
    Maximum-a-posteriori (MAP) methods, while being a standard choice for many estimation problems, have been considered problematic for blind image deblurring: They have been suspected of preferring blurry images to sharp ones. Alternative methods without this apparent defect have been proposed instead. Reservations about MAP methods for blind image deblurring persist even as their close relation to these alternatives has become evident. We revisit the literature on this topic and argue that the original rejection of MAP methods was ill-founded. We show that the MAP approach can prefer sharp images over blurry ones. Furthermore, we show experimentally that the MAP approach can in principle achieve deblurring results that are competitive with the allegedly superior methods. We thereby challenge some traditional notions of the relevant causes underlying successful blind deblurring to obtain a more accurate understanding of the blind image deblurring problem.
  • Estimating the Information Rate of Noisy Two-Dimensional Constrained Channels
    Item type: Conference Paper
    Molkaraie, Mehdi; Loeliger, Hans-Andrea (2010)
    2010 IEEE International Symposium on Information Theory
    The problem of computing the information rate of noisy two-dimensional constrained source/channel models has been an unsolved problem. In this paper, we propose two Monte Carlo methods for this problem. The first method, which is exact in expectation, combines tree-based Gibbs sampling with importance sampling. The second method uses generalized belief propagation and is shown to yield a good approximation of the information rate.
  • Resolution of Superpositions in EMG Signals using Belief Propagation: Results for the Known Constituent Problem
    Item type: Conference Paper
    Koch, Volker M.; McGill, Kevin C.; Loeliger, Hans-Andrea (2006)
    2006 International Conference of the IEEE Engineering in Medicine and Biology Society
    The problem of resolving superpositions in electromyographic (EMG) signals is considered. The shapes of the motor unit action potentials that make up each superposition are assumed to be known a-priori (known constituent problem). Two different and novel belief propagation algorithms have been developed to solve this problem. These algorithms and simulation results are presented in this paper
  • Long-Horizon Direct Model Predictive Control for Power Converters With State Constraints
    Item type: Journal Article
    Keusch, Raphael; Loeliger, Hans-Andrea; Geyer, Tobias (2024)
    IEEE Transactions on Control Systems Technology
    The article explores a new approach to model predictive control (MPC) where both discrete-level input con-straints and state constraints are expressed in terms of Gaussian variables with unknown variances. The computations boil down to repeating Kalman-type recursions, with linear complexity in the prediction horizon. In consequence, the proposed approach can handle long prediction horizons with both discrete-level input constraints and state constraints, which has been a largely unresolved problem. The article demonstrates and evaluates the application of this approach by applying it to the control problem of a three-level power converter with an LC filter. In this application, long horizons are mandatory to obtain low harmonic current distortions, and certain state constraints must be imposed to prevent damage to the converter. The proposed controller can easily handle 100 or more time steps and is shown to perform remarkably well, not only in the steady state, but also in transients and in the case of a phase-to-ground fault.
  • Binary Control and Digital-to-Analog Conversion Using Composite NUV Priors and Iterative Gaussian Message Passing
    Item type: Conference Paper
    Keusch, Raphael; Malmberg, Hampus; Loeliger, Hans-Andrea (2021)
    ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    The paper proposes a new method to determine a binary control signal for an analog linear system such that the state, or some output, of the system follows a given target trajectory. The method can also be used for digital-to-analog conversion.The heart of the proposed method is a new binary-enforcing NUV prior (normal with unknown variance). The resulting computations, for each planning period, amount to iterating forward-backward Gaussian message passing recursions (similar to Kalman smoothing), with a complexity (per iteration) that is linear in the planning horizon. In consequence, the proposed method is not limited to a short planning horizon.
  • Backward Filtering Forward Deciding in Linear Non-Gaussian State Space Models
    Item type: Conference Paper
    Li, Yun-Peng; Loeliger, Hans-Andrea (2024)
    Proceedings of Machine Learning Research ~ Proceedings of The 27th International Conference on Artificial Intelligence and Statistics
    The paper considers linear state space models with non-Gaussian inputs and/or constraints. As shown previously, NUP representations (normal with unknown parameters) allow to compute MAP estimates in such models by iterating Kalman smoothing recursions. In this paper, we propose to compute such MAP estimates by iterating backward-forward recursions where the forward recursion amounts to coordinate-wise input estimation. The advantages of the proposed approach include faster convergence, no \zero-variance stucking", and easier control of constraint satisfaction. The approach is demonstrated with simulation results of exemplary applications including (i) regression with non-Gaussian priors or constraints on k-th order differences and (ii) control with linearly constrained inputs.
  • Control-Bounded Analog-to-Digital Conversion
    Item type: Journal Article
    Malmberg, Hampus; Wilckens, Georg; Loeliger, Hans-Andrea (2022)
    Circuits, Systems, and Signal Processing
    A control-bounded analog-to-digital converter consists of a linear analog system that is subject to digital control, and a digital filter that estimates the analog input signal from the digital control signals. Such converters have many commonalities with delta-sigma converters, but they can use more general analog filters. The paper describes the operating principle, gives a transfer function analysis, and describes the digital filtering. In addition, the paper discusses two examples of such architectures. The first example is a cascade structure reminiscent of, but simpler than, a high-order MASH converter. The second example combines two attractive properties that have so far been considered incompatible. Its nominal conversion noise (assuming ideal components) essentially equals that of the first example. However, its analog filter is a fully connected network to which the input signal is fed in parallel, which potentially makes it more robust against nonidealities.
Publications 1 - 10 of 21