Search Results for author:
Found 25 papers, 17 papers with code
Scalable and Provably Fair Exposure Control for Large-Scale Recommender Systems
Typical recommendation and ranking methods aim to optimize the satisfaction of users, but they are often oblivious to their impact on the items (e. g., products, jobs, news, video) and their providers.
POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition
We also show that POTEC provides a strict generalization of policy- and regression-based approaches and their associated assumptions.
Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction
The PseudoInverse (PI) estimator has been introduced to mitigate the variance issue by assuming linearity in the reward function, but this can result in significant bias as this assumption is hard-to-verify from observed data and is often substantially violated.
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation
This paper introduces SCOPE-RL, a comprehensive open-source Python software designed for offline reinforcement learning (offline RL), off-policy evaluation (OPE), and selection (OPS).
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
Existing evaluation metrics for OPE estimators primarily focus on the "accuracy" of OPE or that of downstream policy selection, neglecting risk-return tradeoff in the subsequent online policy deployment.
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior
We show that the resulting estimator, which we call Adaptive IPS (AIPS), can be unbiased under any complex user behavior.
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling
To circumvent this variance issue, we propose a new estimator, called OffCEM, that is based on the conjunct effect model (CEM), a novel decomposition of the causal effect into a cluster effect and a residual effect.
Policy-Adaptive Estimator Selection for Off-Policy Evaluation
Although many estimators have been developed, there is no single estimator that dominates the others, because the estimators' accuracy can vary greatly depending on a given OPE task such as the evaluation policy, number of actions, and noise level.
Fair Ranking as Fair Division: Impact-Based Individual Fairness in Ranking
Our axioms of envy-freeness and dominance over uniform ranking postulate that for a fair ranking policy every item should prefer their own rank allocation over that of any other item, and that no item should be actively disadvantaged by the rankings.
A Real-World Implementation of Unbiased Lift-based Bidding System
Second, thepractical usefulness of lift-based bidding is not widely understood in the online advertising industry due to the lack of a comprehensive investigation of its impact. We here propose a practically-implementable lift-based bidding system that perfectly fits the current billing rules.
Off-Policy Evaluation for Large Action Spaces via Embeddings
Unfortunately, when the number of actions is large, existing OPE estimators -- most of which are based on inverse propensity score weighting -- degrade severely and can suffer from extreme bias and variance.
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model
We show that the proposed estimator is unbiased in more cases compared to existing estimators that make stronger assumptions.
Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service
As proof of concept, we use our procedure to select the best estimator to evaluate coupon treatment policies on a real-world online content delivery service.
Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation
In this position paper, we explore the potential of using simulation to accelerate practical research of offline RL and OPE, particularly in RecSys and RTB.
Evaluating the Robustness of Off-Policy Evaluation
Unfortunately, identifying a reliable estimator from results reported in research papers is often difficult because the current experimental procedure evaluates and compares the estimators' performance on a narrow set of hyperparameters and evaluation policies.
Optimal Off-Policy Evaluation from Multiple Logging Policies
We study off-policy evaluation (OPE) from multiple logging policies, each generating a dataset of fixed size, i. e., stratified sampling.
Multi-Source Unsupervised Hyperparameter Optimization
How can we conduct efficient hyperparameter optimization for a completely new task?
Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation
Our dataset is unique in that it contains a set of multiple logged bandit datasets collected by running different policies on the same platform.
Unbiased Lift-based Bidding System
Rather, the bidding strategy that leads to the maximum revenue is a strategy pursuing the performance lift of showing ads to a specific user.
Efficient Hyperparameter Optimization under Multi-Source Covariate Shift
This assumption is, however, often violated in uncertain real-world applications, which motivates the study of learning under covariate shift.
Towards Resolving Propensity Contradiction in Offline Recommender Learning
We study offline recommender learning from explicit rating feedback in the presence of selection bias.
Dual Learning Algorithm for Delayed Conversions
To overcome these challenges, we propose two unbiased estimators: one for CVR prediction and the other for bias estimation.
Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models
We study the model selection problem in conditional average treatment effect (CATE) prediction.
Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback
Subsequently, we analyze the variance of the proposed unbiased estimator and further propose a clipped estimator that includes the unbiased estimator as a special case.
Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback
A well-established solution for the problem is using propensity scoring techniques.
