Urmăriți
Sajad Khodadadian
Sajad Khodadadian
Assistant Professor, Virginia Tech
Adresă de e-mail confirmată pe vt.edu - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Fairness in supervised learning: An information theoretic approach
AE Ghassami, S Khodadadian, N Kiyavash
2018 IEEE international symposium on information theory (ISIT), 176-180, 2018
612018
On the linear convergence of natural policy gradient algorithm
S Khodadadian, PR Jhunjhunwala, SM Varma, ST Maguluri
2021 60th IEEE Conference on Decision and Control (CDC), 3794-3799, 2021
502021
Federated reinforcement learning: Linear speedup under markovian sampling
S Khodadadian, P Sharma, G Joshi, ST Maguluri
International Conference on Machine Learning, 10997-11057, 2022
452022
Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm
S Khodadadian, TT Doan, ST Maguluri, J Romberg
arXiv preprint arXiv:2101.10506, 2021
382021
Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm
S Khodadadian, Z Chen, ST Maguluri
arXiv preprint arXiv:2102.09318, 2021
332021
Finite-sample analysis of off-policy natural actor–critic with linear function approximation
Z Chen, S Khodadadian, ST Maguluri
IEEE Control Systems Letters 6, 2611-2616, 2022
272022
On linear and super-linear convergence of natural policy gradient algorithm
S Khodadadian, PR Jhunjhunwala, SM Varma, ST Maguluri
Systems & Control Letters 164, 105214, 2022
152022
Multifractal detrended fluctuation analysis of continuous neural time series in primate visual cortex
Z Fayyaz, M Bahadorian, J Doostmohammad, V Davoodnia, ...
Journal of neuroscience methods, 2018
132018
Information theoretic measures for fairness-aware feature selection
S Khodadadian, M Nafea, AE Ghassami, N Kiyavash
arXiv preprint arXiv:2106.00772, 2021
102021
Impact of data processing on fairness in supervised learning
S Khodadadian, AE Ghassami, N Kiyavash
2021 IEEE International Symposium on Information Theory (ISIT), 2643-2648, 2021
52021
Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noise
SU Haque, S Khodadadian, ST Maguluri
arXiv preprint arXiv:2401.00364, 2023
32023
Backward Curriculum Reinforcement Learning
KM Ko
2023 32nd IEEE International Conference on Robot and Human Interactive …, 2023
2023
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–12