19 citations · 53 across the 21 of their papers we have counts for
21 papers
Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability
Céline Comte, Matthieu Jonckheere, Jaron Sanders +1
In this paper, we introduce a policy-gradient method for model-based reinforcement learning (RL) that exploits a type of stationary distributions commonly obtained from Markov deci…
Noise-Resilient Designs for Optical Neural Networks
Gianluca Kosmella, Ripalta Stabile, Jaron Sanders
All analog signal processing is fundamentally subject to noise, and this is also the case in modern implementations of Optical Neural Networks (ONNs). Therefore, to mitigate noise…
Sharp concentration for sums of matrices with Markovian dependence through universality
Alexander Van Werde, Jaron Sanders
We prove that a sum of random matrices generated by a -mixing Markov chain has similar spectral properties to a Gaussian matrix with the same mean and covariance structure. This…
Detection and Evaluation of Clusters within Sequential Data
Alexander Van Werde, Albert Senen-Cerda, Gianluca Kosmella +1
Sequential data is ubiquitous -- it is routinely gathered to gain insights into complex processes such as behavioral, biological, or physical processes. Challengingly, such data no…
Singular value distribution of dense random matrices with block Markovian dependence
Jaron Sanders, Alexander Van Werde
A block Markov chain is a Markov chain whose state space can be partitioned into a finite number of clusters such that the transition probabilities only depend on the clusters. Blo…
Spectral norm bounds for block Markov chain random matrices
Jaron Sanders, Albert Senen-Cerda
This paper quantifies the asymptotic order of the largest singular value of a centered random matrix built from the path of a Block Markov Chain (BMC). In a BMC there are label…
Universal Approximation in Dropout Neural Networks
Oxana A. Manita, Mark A. Peletier, Jacobus W. Portegies +2
We prove two universal approximation theorems for a range of dropout neural networks. These are feed-forward neural networks in which each edge is given a random -valued f…
Asymptotic convergence rate of Dropout on shallow linear neural networks
Albert Senen-Cerda, Jaron Sanders
We analyze the convergence rate of gradient flows on objective functions induced by Dropout and Dropconnect, when applying them to shallow linear Neural Networks (NNs) - which can…
Modeling Rydberg Gases using Random Sequential Adsorption on Random Graphs
Daan Rutten, Jaron Sanders
The statistics of strongly interacting, ultracold Rydberg gases are governed by the interplay of two factors: geometrical restrictions induced by blockade effects, and quantum mech…
Almost Sure Convergence of Dropout Algorithms for Neural Networks
Albert Senen-Cerda, Jaron Sanders
We investigate the convergence and convergence rate of stochastic training algorithms for Neural Networks (NNs) that have been inspired by Dropout (Hinton et al., 2012). With the g…
Markov chains and hitting times for error accumulation in quantum circuits
Long Ma, Jaron Sanders
We study a classical model for the accumulation of errors in multi-qubit quantum computations. By modeling the error process in a quantum computation using two coupled Markov chain…
Clustering in Block Markov Chains
Jaron Sanders, Alexandre Proutière, Se-Young Yun
This paper considers cluster detection in Block Markov Chains (BMCs). These Markov chains are characterized by a block structure in their transition matrix. More precisely, the …
Scaling Limits and Generic Bounds for Exploration Processes
Paola Bermolen, Matthieu Jonckheere, Jaron Sanders
We consider exploration algorithms of the random sequential adsorption type both for homogeneous random graphs and random geometric graphs based on spatial Poisson processes. At ea…
Optimality gaps in asymptotic dimensioning of many-server systems
Jaron Sanders, S. C. Borst, A. J. E. M. Janssen +1
The Quality-and-Efficiency-Driven (QED) regime provides a basis for solving asymptotic dimensioning problems that trade off revenue, costs and service quality. We derive bounds for…
Sub-Poissonian Statistics of Jamming Limits in Ultracold Rydberg Gases
Jaron Sanders, Matthieu Jonckheere, Servaas Kokkelmans
Several recent experiments have established by measuring the Mandel Q parameter that the number of Rydberg excitations in ultracold gases exhibits sub-Poissonian statistics. This e…
Scaling limits for exploration algorithms
Paola Bermolen, Matthieu Jonckheere, Jaron Sanders
We consider an exploration algorithm where at each step, a random number of items become active while related items get explored. Given an initial number of items growing to in…
Optimal Admission Control for Many-Server Systems with QED-Driven Revenues
Jaron Sanders, S. C. Borst, A. J. E. M. Janssen +1
We consider Markovian many-server systems with admission control operating in a QED regime, where the relative utilization approaches unity while the number of servers grows large,…
Wireless network control of interacting Rydberg atoms
Jaron Sanders, Rick van Bijnen, Edgar Vredenbregt +1
We identify a relation between the dynamics of ultracold Rydberg gases in which atoms experience a strong dipole blockade and spontaneous emission, and a stochastic process that mo…
Scaled control in the QED regime
A. J. E. M. Janssen, J. S. H. van Leeuwaarden, Jaron Sanders
We develop many-server asymptotics in the QED regime for models with admission control. The admission control, designed to reduce the incoming traffic in periods of congestion, sca…
Achievable Performance in Product-Form Networks
Jaron Sanders, Sem C. Borst, Johan S. H. van Leeuwaarden
We characterize the achievable range of performance measures in product-form networks where one or more system parameters can be freely set by a network operator. Given a product-f…
Online Optimization of Product-Form Networks
Jaron Sanders, Sem C. Borst, Johan S. H. van Leeuwaarden
We develop an online gradient algorithm for optimizing the performance of product-form networks through online adjustment of control parameters. The use of standard algorithms for…