Search Results for author:
Found 20 papers, 5 papers with code
Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients
Kakade's natural policy gradient method has been studied extensively in the last years showing linear convergence with and without regularization.
Achieving High Accuracy with PINNs via Energy Natural Gradients
We propose energy natural gradient descent, a natural gradient method with respect to a Hessian-induced Riemannian metric as an optimization algorithm for physics-informed neural networks (PINNs) and the deep Ritz method.
Age structure, replicator equation, and the prisoner's dilemma
These time scales, which seem to form a universal structure in the interplay of weak selection and life-history traits, allow us to reduce the infinite dimensional model to a one-dimensional modified replicator equation.
Geometry and convergence of natural policy gradient methods
We study the convergence of several natural policy gradient (NPG) methods in infinite-horizon discounted Markov decision processes with regular policy parametrizations.
Extrinsic Camera Calibration with Semantic Segmentation
Our approach relies on a coarse initial measurement of the camera pose and builds on lidar sensors mounted on a vehicle with high-precision localization to capture a point cloud of the camera environment.
Invariance Properties of the Natural Gradient in Overparametrised Systems
The natural gradient field is a vector field that lives on a model equipped with a distinguished Riemannian metric, e. g. the Fisher-Rao metric, and represents the direction of steepest ascent of an objective function on the model with respect to this metric.
Self-Assessment for Single-Object Tracking in Clutter Using Subjective Logic
Therefore, this work presents a novel method for self-assessment of single-object tracking in clutter based on Kalman filtering and subjective logic.
Solving infinite-horizon POMDPs with memoryless stochastic policies in state-action space
Reward optimization in fully observable Markov decision processes is equivalent to a linear program over the polytope of state-action frequencies.
Deep Reinforcement Learning for Data-Driven Adaptive Scanning in Ptychography
We present a method that lowers the dose required for a ptychographic reconstruction by adaptively scanning the specimen, thereby providing the required spatial information redundancy in the regions of highest importance.
A model of opinion dynamics with echo chambers explains the spatial distribution of vaccine hesitancy
Vaccination hesitancy is a major obstacle to achieving and maintaining herd immunity.
Life-History traits and the replicator equation
In this context, it is fundamentally of interest to generalize the replicator equation, which is at the heart of most population genomics models.
The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs
We then describe the optimization problem as a linear optimization problem in the space of feasible state-action frequencies subject to polynomial constraints that we characterize explicitly.
Error Estimates for the Deep Ritz Method with Boundary Penalty
Our results apply to arbitrary sets of ansatz functions and estimate the error in dependence of the optimization accuracy, the approximation capabilities of the ansatz class and -- in the case of Dirichlet boundary values -- the penalization strength $\lambda$.
Contact Tracing & Super-Spreaders in the Branching-Process Model
We investigate a novel model for super-spreader events, not based on a heterogeneous contact graph but on a random contact rate: Many individuals become infected synchronously in single contact events.
Kalman Filter Meets Subjective Logic: A Self-Assessing Kalman Filter Using Subjective Logic
Thus, by embedding classical Kalman filtering into subjective logic, our method additionally features an explicit measure for statistical uncertainty in the self-assessment.
Deep Ritz revisited
In this notes we use the notion of $\Gamma$-convergence to show that ReLU networks of growing architecture that are trained with respect to suitably regularised Dirichlet energies converge to the true solution of the Poisson problem.
LACI: Low-effort Automatic Calibration of Infrastructure Sensors
While classical approaches are sensor-specific and often need calibration targets as well as a widely overlapping field of view (FOV), within this work, a cooperative intelligent vehicle is used as callibration target.
On the space-time expressivity of ResNets
This structure can be seen as the Euler discretisation of an associated ordinary differential equation (ODE) which is called a neural ODE.
Multi-scale Convolutional Neural Networks for Inverse Problems
We propose a novel neural network architecture highlighting fast convergence as a generic solution addressing image(s)-to-image(s) inverse problems of different domains.
Computational Physics Materials Science
Speeding up SOR Solvers for Constraint-based GUIs with a Warm-Start Strategy
Constraints are a powerful tool for specifying adaptable GUI layouts: they are used to specify a layout in a general form, and a constraint solver is used to find a satisfying concrete layout, e. g.\ for a specific GUI size.
