Statistical hypothesis testing based on machine learning: Large deviations analysis
We study the performance of Machine Learning (ML) classification techniques. Leveraging
the theory of large deviations, we provide the mathematical conditions for a ML classifier to …
the theory of large deviations, we provide the mathematical conditions for a ML classifier to …
[PDF][PDF] Optimal clustering with bandit feedback
This paper considers the problem of online clustering with bandit feedback. A set of arms (or
items) can be partitioned into various groups that are unknown. Within each group, the …
items) can be partitioned into various groups that are unknown. Within each group, the …
Best arm identification in restless Markov multi-armed bandits
We study the problem of identifying the best arm in a multi-armed bandit environment when
each arm is a time-homogeneous and ergodic discrete-time Markov process on a common …
each arm is a time-homogeneous and ergodic discrete-time Markov process on a common …
Detecting an odd restless Markov arm with a trembling hand
PN Karthik, R Sundaresan - IEEE Transactions on Information …, 2021 - ieeexplore.ieee.org
In this paper, we consider a multi-armed bandit in which each arm is a Markov process
evolving on a finite state space. The state space is common across the arms, and the arms …
evolving on a finite state space. The state space is common across the arms, and the arms …
Optimal Best Arm Identification with Fixed Confidence in Restless Bandits
We study best arm identification in a restless multi-armed bandit setting with finitely many
arms. The discrete-time data generated by each arm forms a homogeneous Markov chain …
arms. The discrete-time data generated by each arm forms a homogeneous Markov chain …
A GNSS/SINS fault detection and robust adaptive algorithm based on sliding average smooth bounded layer width
G Zhao, J Wang, S Gao, Z Jiang - … Science and Technology, 2024 - new.iopscience.iop.org
Abstract The Global Navigation Satellite System/Strapdown Inertial Navigation System
(GNSS/SINS) integrated navigation system is an important technology for UAV …
(GNSS/SINS) integrated navigation system is an important technology for UAV …
A General Framework for Clustering and Distribution Matching with Bandit Feedback
We develop a general framework for clustering and distribution matching problems with
bandit feedback. We consider a $ K $-armed bandit model where some subset of $ K $ arms …
bandit feedback. We consider a $ K $-armed bandit model where some subset of $ K $ arms …
Optimal Best Arm Identification with Fixed Confidence in Restless Bandits
We study best arm identification in a restless multi-armed bandit setting with finitely many
arms. The discrete-time data generated by each arm forms a homogeneous Markov chain …
arms. The discrete-time data generated by each arm forms a homogeneous Markov chain …
Asymptotically optimal sequential anomaly identification with ordering sampling rules
A Tsopelakos, G Fellouris - arXiv preprint arXiv:2309.14528, 2023 - arxiv.org
The problem of sequential anomaly detection and identification is considered in the
presence of a sampling constraint. Specifically, multiple data streams are generated by …
presence of a sampling constraint. Specifically, multiple data streams are generated by …
A New Framework for Evaluating the Validity and the Performance of Binary Decisions on Manifold-Valued Data
In this paper, we introduce a new framework that can be used for evaluating the validity and
the performance of machine learning models on manifold-valued data. More particularly, two …
the performance of machine learning models on manifold-valued data. More particularly, two …