Seguir
Mohammad Mehrabi
Mohammad Mehrabi
Graduate School of Business, Stanford University
E-mail confirmado em stanford.edu - Página inicial
Título
Citado por
Citado por
Ano
Online debiasing for adaptively collected high-dimensional data with applications to time series analysis
Y Deshpande, A Javanmard, M Mehrabi
Journal of the American Statistical Association, 1-14, 2021
40*2021
Fundamental tradeoffs in distributionally adversarial training
M Mehrabi, A Javanmard, RA Rossi, A Rao, T Mai
International Conference on Machine Learning, 7544-7554, 2021
272021
Bounds on the approximation power of feedforward neural networks
M Mehrabi, A Tchamkerten, M Yousefi
International Conference on Machine Learning, 3453-3461, 2018
112018
Error-correction for sparse support recovery algorithms
M Mehrabi, A Tchamkerten
IEEE Transactions on Information Theory 68 (11), 7396-7409, 2022
102022
Over-the-air federated learning exploiting channel perturbation
SM Hamidi, M Mehrabi, AK Khandani, D Gündüz
2022 IEEE 23rd International Workshop on Signal Processing Advances in …, 2022
92022
Adversarial robustness for latent models: Revisiting the robust-standard accuracies tradeoff
A Javanmard, M Mehrabi
Operations Research 72 (3), 1016-1030, 2024
82024
Pearson chi-squared conditional randomization test
A Javanmard, M Mehrabi
arXiv preprint arXiv:2111.00027, 2021
52021
Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap
M Mehrabi, S Wager
arXiv preprint arXiv:2402.08201, 2024
22024
Optimal Mechanisms for Demand Response: An Indifference Set Approach
M Mehrabi, O Karaduman, S Wager
arXiv preprint arXiv:2409.07655, 2024
2024
GRASP: a goodness-of-fit test for classification learning
A Javanmard, M Mehrabi
Journal of the Royal Statistical Society Series B: Statistical Methodology …, 2024
2024
A model-free closeness-of-influence test for features in supervised learning
M Mehrabi, RA Rossi
International Conference on Machine Learning, 24304-24324, 2023
2023
O sistema não pode executar a operação agora. Tente novamente mais tarde.
Artigos 1–11