Search Results for author:
Found 16 papers, 5 papers with code
Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits
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.
Calibration-then-Calculation: A Variance Reduced Metric Framework in Deep Click-Through Rate Prediction Models
The metric variance comes from the randomness inherent in the training process of deep learning pipelines.
Seller-Side Experiments under Interference Induced by Feedback Loops in Two-Sided Platforms
Two-sided platforms are central to modern commerce and content sharing and often utilize A/B testing for developing new features.
Singular Control of (Reflected) Brownian Motion: A Computational Method Suitable for Queueing Applications
Motivated by applications in queueing theory, we consider a class of singular stochastic control problems whose state space is the d-dimensional positive orthant.
On the Foundation of Distributionally Robust Reinforcement Learning
This is accomplished through a comprehensive modeling framework centered around distributionally robust Markov decision processes (DRMDPs).
Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach
In modern recommendation systems, the standard pipeline involves training machine learning models on historical data to predict user behaviors and improve recommendations continuously.
Drift Control of High-Dimensional RBM: A Computational Method Based on Neural Networks
Motivated by applications in queueing theory, we consider a stochastic control problem whose state space is the $d$-dimensional positive orthant.
Sample Complexity of Variance-reduced Distributionally Robust Q-learning
Further, the variance-reduced distributionally robust Q-learning combines the synchronous Q-learning with variance-reduction techniques to enhance its performance.
A Finite Sample Complexity Bound for Distributionally Robust Q-learning
We consider a reinforcement learning setting in which the deployment environment is different from the training environment.
Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems
Calibration is defined as the ratio of the average predicted click rate to the true click rate.
Selecting the Best Optimizing System
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.
Testing Group Fairness via Optimal Transport Projections
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions.
Quantifying the Empirical Wasserstein Distance to a Set of Measures: Beating the Curse of Dimensionality
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.
Robust Bayesian Classification Using an Optimistic Score Ratio
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.
Distributionally Robust Batch Contextual Bandits
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.
Confidence Regions in Wasserstein Distributionally Robust Estimation
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.
