Contact
On Restless Linear Bandits
A more general formulation of the linear bandit problem is considered to allow for dependencies over time. Specifically, it is assumed that there exists an unknown Rd -valued stationary φ -mixing seq ...
IEEE Transactions on Information Theory ( Volume: 71, Issue: 4, April 2025), 2025
Hasimoto frames and the Gibbs measure of the periodic nonlinear Schrödinger equation
The paper interprets the cubic nonlinear Schrödinger equation as a Hamiltonian system with infinite dimensional phase space. There exists a Gibbs measure which is invariant under the flow associated ...
J. Math. Phys. 65, 022705 (2024), 2024
Estimating the Mixing Coefficients of Geometrically Ergodic Markov Processes
We propose methods to estimate the individual β-mixing coefficients of a real-valued geometrically ergodic Markov process from a single sample-path X0,X1,...,Xn. Under standard smoothness conditions ...
arXiv:2402.07296v1 [math.ST] , 2024
Inferring the Mixing Properties of a Stationary Ergodic Process From a Single Sample-Path
We propose strongly consistent estimators of the ℓ1 norm of the sequence of α -mixing (respectively β -mixing) coefficients of a stationary ergodic process. We further provide strongly consistent ...
IEEE Transactions on Information Theory ( Volume: 69, Issue: 6, June 2023), 2023
Oblivious Data for Fairness with Kernels
We investigate the problem of algorithmic fairness in the case where sensitive and non-sensitive features are available and one aims to generate new, ‘oblivious’, features that closely approximate ...
Journal of Machine Learning Research 22 (2021) 1-36, 2021
Clustering piecewise stationary processes
The problem of time-series clustering is considered in the case where each data-point is a sample generated by a piecewise stationary process. While stationary processes comprise one of the most gener ...
2020 IEEE International Symposium on Information Theory (ISIT), 2020
Approximations of the Restless Bandit Problem
The multi-armed restless bandit problem is studied in the case where the pay-off distributions are stationary-mixing. This version of the problem provides a more realistic model for most real-world ap ...
Journal of Machine Learning Research 20 (2019) 1-37, 2019
Consistent Algorithms for Clustering Time Series
The problem of clustering is considered for the case where every point is a time series. The time series are either given in one batch (o ine setting), or they are allowed to grow with time and new ti ...
Journal of Machine Learning Research 17 (2016) 1-32, 2016
Nonparametric multiple change point estimation in highly dependent time series
Given a heterogeneous time-series sample, the objective is to find points in time, called change points, where the probability distribution generating the data has changed. The data are assumed to hav ...
Theoretical Computer Science Volume 620, 21 March 2016, Pages 119-133, 2016
Asymptotically consistent estimation of the number of change points in highly dependent time series
The problem of change point estimation is considered in a general framework where the data are generated by arbitrary unknown stationary ergodic process distributions. This means that the data may hav ...
Proceedings of the 31st International Conference on Machine Learning, PMLR 32(1):539-547, 2014