no code implementations • ICML 2020 • Nian Si, Fan Zhang, Zhengyuan Zhou, Jose Blanchet
We first present a policy evaluation procedure in the ambiguous environment and also give a heuristic algorithm to solve the distributionally robust policy learning problems efficiently.
no code implementations • 30 Jan 2024 • Yewen Fan, Nian Si, Xiangchen Song, Kun Zhang
The metric variance comes from the randomness inherent in the training process of deep learning pipelines.
no code implementations • 29 Jan 2024 • Zhihua Zhu, Zheng Cai, Liang Zheng, Nian Si
Two-sided platforms are central to modern commerce and content sharing and often utilize A/B testing for developing new features.
1 code implementation • 19 Dec 2023 • Baris Ata, J. Michael Harrison, Nian Si
Motivated by applications in queueing theory, we consider a class of singular stochastic control problems whose state space is the d-dimensional positive orthant.
no code implementations • 15 Nov 2023 • Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
This is accomplished through a comprehensive modeling framework centered around distributionally robust Markov decision processes (DRMDPs).
no code implementations • 26 Oct 2023 • Nian Si
In modern recommendation systems, the standard pipeline involves training machine learning models on historical data to predict user behaviors and improve recommendations continuously.
1 code implementation • 20 Sep 2023 • Baris Ata, J. Michael Harrison, Nian Si
Motivated by applications in queueing theory, we consider a stochastic control problem whose state space is the $d$-dimensional positive orthant.
no code implementations • 28 May 2023 • Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
Further, the variance-reduced distributionally robust Q-learning combines the synchronous Q-learning with variance-reduction techniques to enhance its performance.
no code implementations • 26 Feb 2023 • Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
We consider a reinforcement learning setting in which the deployment environment is different from the training environment.
1 code implementation • 19 May 2022 • Yewen Fan, Nian Si, Kun Zhang
Calibration is defined as the ratio of the average predicted click rate to the true click rate.
1 code implementation • 9 Jan 2022 • Nian Si, Zeyu Zheng
An SBOS problem compares different systems based on their expected performances under their own optimally chosen decision to select the best, without advance knowledge of expected performances of the systems nor the optimizing decision inside each system.
no code implementations • 2 Jun 2021 • Nian Si, Karthyek Murthy, Jose Blanchet, Viet Anh Nguyen
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions.
no code implementations • NeurIPS 2020 • Nian Si, Jose Blanchet, Soumyadip Ghosh, Mark Squillante
We consider the problem of estimating the Wasserstein distance between the empirical measure and a set of probability measures whose expectations over a class of functions (hypothesis class) are constrained.
1 code implementation • ICML 2020 • Viet Anh Nguyen, Nian Si, Jose Blanchet
The optimistic score searches for the distribution that is most plausible to explain the observed outcomes in the testing sample among all distributions belonging to the contextual ambiguity set which is prescribed using a limited structural constraint on the mean vector and the covariance matrix of the underlying contextual distribution.
no code implementations • 10 Jun 2020 • Nian Si, Fan Zhang, Zhengyuan Zhou, Jose Blanchet
Leveraging this evaluation scheme, we further propose a novel learning algorithm that is able to learn a policy that is robust to adversarial perturbations and unknown covariate shifts with a performance guarantee based on the theory of uniform convergence.
no code implementations • 4 Jun 2019 • Jose Blanchet, Karthyek Murthy, Nian Si
Wasserstein distributionally robust optimization estimators are obtained as solutions of min-max problems in which the statistician selects a parameter minimizing the worst-case loss among all probability models within a certain distance (in a Wasserstein sense) from the underlying empirical measure.