Search Results for author:
Found 46 papers, 5 papers with code
Debiased Regression for Root-N-Consistent Conditional Mean Estimation
Notably, this approach remains model-free as long as the original estimator and the conditional expected residual estimator satisfy the convergence rate condition.
A Note on Doubly Robust Estimator in Regression Continuity Designs
A common approach in RD estimation is the use of nonparametric regression methods, such as local linear regression.
Conformal Predictive Portfolio Selection
This study explores portfolio selection using predictive models for portfolio returns.
Adaptive Generalized Neyman Allocation: Local Asymptotic Minimax Optimal Best Arm Identification
This study investigates a local asymptotic minimax optimal strategy for fixed-budget best arm identification (BAI).
Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choices
First, we derive the efficient covariate density and propensity score that minimize the semiparametric efficiency bound and find that optimizing both covariate density and propensity score minimizes the semiparametric efficiency bound more effectively than optimizing only the propensity score.
Triple/Debiased Lasso for Statistical Inference of Conditional Average Treatment Effects
In high-dimensional linear regression, one typical approach is to assume sparsity.
LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
For this issue, this study proposes an algorithm whose regret satisfies $O(\log(T))$ in the setting when the suboptimality gap is lower-bounded.
A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees
We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs).
Adaptive Experimental Design for Policy Learning
Setting the worst-case expected regret as the performance criterion of adaptive sampling and recommended policies, we derive its asymptotic lower bounds, and propose a strategy, Adaptive Sampling-Policy Learning strategy (PLAS), whose leading factor of the regret upper bound aligns with the lower bound as the size of experimental units increases.
Best-of-Both-Worlds Linear Contextual Bandits
The goal of this study is to develop a strategy that is effective in both stochastic and adversarial environments, with theoretical guarantees.
Locally Optimal Fixed-Budget Best Arm Identification in Two-Armed Gaussian Bandits with Unknown Variances
They also propose a strategy, assuming that the variances of rewards are known, and show that it is asymptotically optimal in the sense that its probability of misidentification matches the lower bound as the budget approaches infinity.
Worst-Case Optimal Multi-Armed Gaussian Best Arm Identification with a Fixed Budget
Because available information is limited in actual experiments, we develop a lower bound that is valid under the unknown means and the unknown choice of the best arm, which are referred to as the worst-case lower bound.
Double Debiased Covariate Shift Adaptation Robust to Density-Ratio Estimation
For this problem, existing studies have proposed covariate shift adaptation via importance weighting using the density ratio.
CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression
This study assumes two linear regression models between a potential outcome and covariates of the two treatments and defines CATEs as a difference between the linear regression models.
Asymptotically Unbiased Synthetic Control Methods by Distribution Matching
Based on this assumption, we estimate SC weights by matching the moments of treated outcomes with the weighted sum of moments of untreated outcomes.
Automatic Debiased Learning from Positive, Unlabeled, and Exposure Data
Therefore, the positive labels that we observe are a combination of both the exposure and the labeling, which creates a selection bias problem for the observed positive samples.
Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds
We evaluate the decision based on the expected simple regret, which is the difference between the expected outcomes of the best arm and the recommended arm.
Best Arm Identification with Contextual Information under a Small Gap
We then develop the ``Random Sampling (RS)-Augmented Inverse Probability weighting (AIPW) strategy,'' which is asymptotically optimal in the sense that the probability of misidentification under the strategy matches the lower bound when the budget goes to infinity in the small-gap regime.
Bayesian Spatial Predictive Synthesis
Spatial data are characterized by their spatial dependence, which is often complex, non-linear, and difficult to capture with a single model.
Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression
We study the benign overfitting theory in the prediction of the conditional average treatment effect (CATE), with linear regression models.
Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics
This paper provides a unified perspective for the Kullback-Leibler (KL)-divergence and the integral probability metrics (IPMs) from the perspective of maximum likelihood density-ratio estimation (DRE).
Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap
We show that a strategy following the Neyman allocation rule (Neyman, 1934) is asymptotically optimal when the gap between the expected rewards is small.
The Adaptive Doubly Robust Estimator and a Paradox Concerning Logging Policy
This paper proposes a DR estimator for dependent samples obtained from adaptive experiments.
Rate-optimal Bayesian Simple Regret in Best Arm Identification
We consider best arm identification in the multi-armed bandit problem.
Learning Causal Relationships from Conditional Moment Restrictions by Importance Weighting
We consider learning causal relationships under conditional moment restrictions.
Policy Choice and Best Arm Identification: Asymptotic Analysis of Exploration Sampling
We consider the "policy choice" problem -- otherwise known as best arm identification in the bandit literature -- proposed by Kasy and Sautmann (2021) for adaptive experimental design.
Learning Causal Models from Conditional Moment Restrictions by Importance Weighting
To address this issue, we propose a method that transforms conditional moment restrictions to unconditional moment restrictions through importance weighting, using a conditional density ratio estimator.
The Role of Contextual Information in Best Arm Identification
We demonstrate that contextual information can be used to improve the efficiency of the identification of the best marginalized mean reward compared with the results of Garivier & Kaufmann (2016).
Scalable Personalised Item Ranking through Parametric Density Estimation
However, such methods have two main drawbacks particularly in large-scale applications; (1) the pairwise approach is severely inefficient due to the quadratic computational cost; and (2) even recent model-based samplers (e. g. IRGAN) cannot achieve practical efficiency due to the training of an extra model.
Adaptive Doubly Robust Estimator from Non-stationary Logging Policy under a Convergence of Average Probability
To mitigate this limitation, we propose another assumption that the average logging policy converges to a time-invariant function and show the doubly robust (DR) estimator's asymptotic normality.
Density-Ratio Based Personalised Ranking from Implicit Feedback
Learning from implicit user feedback is challenging as we can only observe positive samples but never access negative ones.
ATRO: Adversarial Training with a Rejection Option
In this paper, in order to acquire a more reliable classifier against adversarial attacks, we propose the method of Adversarial Training with a Rejection Option (ATRO).
A Practical Guide of Off-Policy Evaluation for Bandit Problems
Based on the properties of the evaluation policy, we categorize OPE situations.
Off-Policy Evaluation of Bandit Algorithm from Dependent Samples under Batch Update Policy
The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy.
The Adaptive Doubly Robust Estimator for Policy Evaluation in Adaptive Experiments and a Paradox Concerning Logging Policy
This paper proposes a DR estimator for dependent samples obtained from adaptive experiments.
Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment
To this end, we propose a method that trains our policy to maximize the expected quadratic utility, defined as a weighted sum of the first and second moments of the rewards obtained through our policy.
Policy Gradient with Expected Quadratic Utility Maximization: A New Mean-Variance Approach in Reinforcement Learning
In this paper, we suggest expected quadratic utility maximization (EQUM) as a new framework for policy gradient style reinforcement learning (RL) algorithms with mean-variance control.
Learning Classifiers under Delayed Feedback with a Time Window Assumption
We consider training a binary classifier under delayed feedback (\emph{DF learning}).
Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
Density ratio estimation (DRE) is at the core of various machine learning tasks such as anomaly detection and domain adaptation.
Confidence Interval for Off-Policy Evaluation from Dependent Samples via Bandit Algorithm: Approach from Standardized Martingales
The goal of OPE is to evaluate a new policy using historical data obtained from behavior policies generated by the bandit algorithm.
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
Then, we propose doubly robust and efficient estimators for OPE and OPL under a covariate shift by using a nonparametric estimator of the density ratio between the historical and evaluation data distributions.
Efficient Adaptive Experimental Design for Average Treatment Effect Estimation
In adaptive experimental design, the experimenter is allowed to change the probability of assigning a treatment using past observations for estimating the ATE efficiently.
Model Specification Test with Unlabeled Data: Approach from Covariate Shift
By applying the proposed method, we can obtain a model that predicts the label for the unlabeled test data well without losing the interpretability of the model.
Learning with Protection: Rejection of Suspicious Samples under Adversarial Environment
Our main idea is to apply a framework of learning with rejection and adversarial examples to assist in the decision making for such suspicious samples.
Learning from Positive and Unlabeled Data with a Selection Bias
However, this assumption is unrealistic in many instances of PU learning because it fails to capture the existence of a selection bias in the labeling process.
Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data
In this paper, we propose a novel unified approach to estimating the class-prior and training a classifier alternately.
