Improves machine translation by learning from user feedback.
problem Avoid showing inferior translations to users.
method Analyze degeneracies of counterfactual learning methods.
result Relates degeneracies to recent counterfactual learning techniques.
Proposes stabilized weights for causal inference using isotonic calibration.
problem Stability and bias issues in inverse propensity weighting.
method Post-hoc isotonic calibration of inverse propensity weights.
result Improves performance of doubly robust estimators of average treatment effect.
Paper proposes CounterSample to improve convergence in LTR models.
problem Large variance in IPS weights slows convergence in LTR models.
method Introduces CounterSample algorithm with provably better convergence.
result CounterSample converges faster than standard IPS-weighted methods.
AIPS improves ranking policy evaluation by adapting to diverse user behavior.
problem Inaccurate Off-Policy Evaluation of ranking policies due to high variance under diverse user behavior.
method Developed Adaptive IPS (AIPS) that adapts to different user behaviors and minimizes MSE.
result AIPS achieves minimum variance among unbiased estimators and provides significant empirical accuracy improvement.
Paper proposes unbiased learning for recommendation causal effects.
problem Estimating the causal effect of recommendation when the ground truth is unobservable.
method Inverse propensity scoring technique to construct unbiased estimators, followed by empirical risk minimization with propensity capping.
result The proposed method outperforms other biased learning methods in various settings.
Proposes a method to correct exposure misclassification bias in Cox models.
problem Challenges in estimating exposure-outcome associations with misclassified exposure data.
method An estimating equation method to correct for exposure misclassification-caused bias.
result Proposed method corrects bias in estimating PM2.5 level's association with lung cancer mortality.
Extends recommender methods to respect capacity constraints.
problem Recommendation under capacity constraints in various settings.
method Extend three state-of-the-art latent factor recommendation approaches (PMF, GeoMF, BPR) to optimize for both recommendation accuracy and expected item usage that respects capacity constraints.
result Experimental results highlight the benefit of the method for recommendation under capacity constraints.
A model predicts user movie preferences based on novelty-seeking traits.
problem Accurately predicting user movie preferences for competitive websites.
method DFNSM model uses demographic, genre, and novelty-seeking data.
result DFNSM outperforms previous models in movie recommendation accuracy.
StableDR stabilizes doubly robust learning for biased recommendation data.
problem Data missing not at random in recommender systems.
method StableDR, a stabilized doubly robust learning approach.
result StableDR achieves bounded bias, variance, and generalization error.
Recommending items to users is a challenging task due to the large amount of missing information. In many cases, the data solely consist of ratings or tags voluntarily contributed by each user on a very limited subset of the available items, so that most of the data of potential interest is actually missing. Current ap…
Study shows how repetition affects learning in bandit settings, providing algorithms with sublinear regret.
problem Effect of persistence of engagement on learning in stochastic multi-armed bandit settings.
method Novel algorithms that achieve sublinear regret under temporal constraints.
result Additive effect of priming on regret upper bound, matching popular algorithms in absence of priming.
We develop a learning principle and an efficient algorithm for batch learning from logged bandit feedback. This learning setting is ubiquitous in online systems (e.g., ad placement, web search, recommendation), where an algorithm makes a prediction (e.g., ad ranking) for a given input (e.g., query) and observes bandit …
New method resolves bias in recommender learning without needing missing data.
problem Bias in offline recommender learning from explicit ratings.
method Proposes a novel algorithm to minimize generalization error bound via adversarial learning, independent of propensity estimation.
result Demonstrates superior performance in rating prediction and ranking metrics without missing completely at random data.
The paper resolves the paradox of using unlabeled data for treatment effect estimation.
problem Using unlabeled data to estimate propensity scores for treatment effect estimation.
method Proposes a simple procedure to reconcile the use of estimated propensity scores with the advice to use true propensity scores.
result Direct regression may be preferable to inverse-propensity weighting in many circumstances.
Estimates users' preference for a site over others using engagement data.
problem Lack of data on users' interactions with other sites makes it hard to estimate preferences for a focal site.
method Uses Hierarchical Bayes Method with two estimation techniques: Markov Chain Monte Carlo and Stochastic Gradient with Langevin Dynamics.
result Good support found for the approach to computing personalized share of engagement.
SCR diversifies recommendations by applying style transfer to user profiles.
problem Diversify personalized recommendations without losing relevance.
method Style injection using Conditional Variational Autoencoder (CVAE) architecture.
result 12% improvement in NDCG@20 and 22% improvement in AUC across all classes.
This study optimizes covariate density and propensity score for efficient ATE estimation.
problem Efficiently estimating average treatment effects (ATEs) with minimal variance.
method Adaptive experiment optimizing both covariate density and propensity score.
result Proposed method minimizes the semiparametric efficiency bound for ATE estimation.
Paper develops consistent estimation of propensity scores for rare exposures.
problem Estimation of propensity score functions for rare exposures in oversampled cohorts.
method Flexible computational implementation using source population probability of exposure and observation weighting.
result Low empirical bias and variance for consistent propensity score function estimators.
Paper proposes methods to reduce bias and variance in recommender systems.
problem Bias in recommender systems due to users' preferences.
method Proposes a principled approach to reduce bias and variance in DR methods, and a novel semi-parametric collaborative learning approach.
result The proposed methods outperform existing debiasing methods in both theory and experiments.
Improves robustness of propensity score estimators in challenging settings.
problem Limited overlap, small sample sizes, or unbalanced data.
method Extends calibration techniques for propensity score models, focusing on sample-splitting schemes.
result Calibration reduces variance and bias in inverse probability weighting and double/debiased machine learning frameworks.
Proposes a meta-learning method to improve recommender systems with biased feedback.
problem Learning from biased feedback in recommender systems.
method Asymmetric tri-training framework for meta-learning, using three predictors.
result Minimizes the upper bound of true performance metric, improving robustness to selection bias.
New estimator GMIPS reduces variance in ranking policy evaluation.
problem High variance in off-policy evaluation for ranking policies.
method GMIPS estimator with user behavior model on ranking embedding spaces.
result GMIPS achieves lowest MSE and balances bias-variance trade-off.
CausalRM models rewards from user feedback, overcoming noise and bias.
problem Aligning language models with user preferences from noisy, biased feedback.
method Causal-theoretic reward modeling framework addressing noise and bias in observational feedback.
result CausalRM learns accurate reward signals from noisy and biased observational feedback.
A new tensor completion method handles missing data with missing not at random entries.
problem Handling missing data in tensors where the probability of observation depends on other entries.
method Estimate propensities using convex relaxation, then use higher-order SVD with inverse propensities weights.
result Finite-sample error bounds on the completed tensor are provided.
FIDDLE uses deep learning to estimate ATE from complex data.
problem Estimating ATE from high-dimensional, correlated covariates with sparse nonlinear effects.
method Factor-augmented deep learning for propensity and outcome models.
result FIDDLE consistently estimates ATE under model misspecification and is semiparametrically efficient.
Propensity score computation improved with machine learning for label-corrupted data.
problem Confounding covariates and label corruption in propensity score computation.
method Spectral clustering followed by Xgboost for propensity score computation.
result Xgboost propensity scores computed with processed data outperform original data.
Three methods for training models on bandit feedback, reviewed and tested.
problem Training machine learning models on recommender system logs.
method Three distinct methods: argmax, distribution adjustment, and inverse propensity score.
result The latter two methods violate principles but perform well in certain settings.
New method improves causal effect estimation by addressing imbalance in training data.
problem Imbalance between treatment and control groups in training data.
method Combines distributionally robust optimization and weight regularization.
result Consistent improvements over existing methods in experiments.
New method reduces confidence interval sizes for causal inference.
problem Inaccurate propensity scores and extreme scores cause large confidence intervals.
method Data-dependent Coarse IPW (CIPW) estimators.
result Robust CIPW estimators reduce confidence interval sizes to ε+1/√n.
Proposes a new IPW-based ranking metric for two-sided markets.
problem Addressing bias in implicit user feedback in two-sided markets.
method Extends IPW estimator to two-sided markets, addressing position bias.
result Proposed estimator is unbiased for ground-truth ranking metric.
New method estimates position bias without manual interventions for better search engine rankings.
problem Presentation bias confounds relevance signals in search engines.
method Proposes a method for consistent propensity estimation without manual relevance judgments.
result Initial studies confirm scalability, accuracy, and robustness of the approach.
Proposes methods to estimate posterior probability and propensity score functions without assuming constant propensity score.
problem Learning from biased positive-unlabeled data.
method Parametric approach to joint estimation of posterior probability and propensity score functions using maximum likelihood and alternating maximization.
result Proposed methods are comparable or better than existing methods based on Expectation-Maximisation scheme.
Proposes a robust method to estimate causal effects with high-dimensional covariates.
problem Estimating causal effects in studies with many confounders.
method Penalized M-estimators for propensity score and outcome models, followed by covariate balancing.
result Root-n consistent, asymptotically normal estimator with semiparametric efficiency.
The paper investigates how calibrating propensity scores improves DML estimates of average treatment effects.
problem Improving the accuracy of DML estimates in finite samples.
method Propensity score calibration within the Double/debiased machine learning framework.
result Calibrating propensity scores reduces the root mean squared error of DML estimates of average treatment effects in finite samples.
Post-calibration improves the accuracy of causal effect estimation.
problem Improperly calibrated propensity scores lead to inaccurate causal effect estimation.
method Performed a simulation study to assess the impact of post-calibration on causal effect estimation.
result Post-calibration reduces the error in estimating the average treatment effect, especially for expressive uncalibrated statistical estimators.
The study explores machine learning for predicting customer propensity-to-pay uncertainty.
problem Improving customer experience, reducing financial hardship, and managing cash flow risks.
method Investigated machine learning models for predicting propensity-to-pay, focusing on uncertainty estimation.
result Novel Bayesian Neural Network model for binary classification of propensity-to-pay.
Propensity score matching improves fairness in machine learning models.
problem Bias in training data affects fairness metrics in machine learning models.
method Propensity score matching to evaluate and mitigate bias in test data.
result FairMatch significantly reduces bias in test data without sacrificing predictive performance.
Quantum approach models economic decisions with probabilistic and dynamic probabilities.
problem Traditional economic models fail to explain recent financial crises.
method Develops a quantum probabilistic framework for economics.
result Quantum circuits can model cognitive phenomena like preference reversal.
A new method uses counterfactual learning to improve recommendation system evaluation.
problem Inconsistent results in recommender systems due to exposure mechanisms.
method Proposes a minimax empirical risk formulation with an adversarial game to account for exposure.
result Shows improved learning bounds and effectiveness over various recommendation settings.
Some general features of kinetic multi-agent models are reviewed, with particular attention to the relation between the agent saving propensities and the form of the equilibrium wealth distribution. The effect of a finite cutoff of the saving propensity distribution on the corresponding wealth distribution is studied. …
We review a simple model of closed economy, where the economic agents make money transactions and a saving criterion is present. We observe the Gibbs distribution for zero saving propensity, and non-Gibbs distributions otherwise. While the exact solution in the case of zero saving propensity is already known to be give…
The paper develops a method to estimate consumer preferences from observed rankings.
problem Estimating consumer preferences from partial ranking information.
method Interpreting observed rankings as pairwise comparisons, modeling latent utility, and correcting for selection bias.
result The method improves recommendation performance, especially for previously unconsumed products.
Paper tackles bias-variance trade-off in missing data, proposing a dynamic framework.
problem Missing data in practical applications deteriorates model performance.
method Develops a fine-grained dynamic learning framework to jointly optimize bias and variance.
result Theoretical and empirical validation of joint bias-variance optimization.
Unified causal inference framework using distribution adaptation.
problem Estimating Average Treatment Effects (ATE) under uncertainty in propensity scores.
method Reframed as domain adaptation problem, using machine learning techniques.
result Joint Robust Estimator (JRE) achieves up to 15% reduction in MSE.
Deep learning improves causal inference methods for treatment effects.
problem Estimating individual and average treatment effects in econometrics.
method Proposed deep learning techniques for propensity score matching and generalized neighbor matching.
result Deep learning methods outperform traditional techniques in estimating treatment effects.
Study introduces a new framework for policy learning without positivity assumption.
problem Learning optimal treatment assignment policies from observational data with constraints.
method Incremental propensity score policies and semiparametric efficiency theory.
result Validated framework's performance through numerical experiments.
The study optimizes free trial lengths to boost subscriptions and consumer loyalty.
problem Optimizing free trial lengths to maximize customer acquisition and retention.
method A large-scale field experiment with personalized policy design and evaluation.
result Personalized free trial policies outperform uniform trial lengths.
CART can bias propensity score estimates with missing data, but multiple imputation is better.
problem Bias in propensity score estimation with CART and missing data.
method Examined CART performance with different approaches to missing data: direct CART, complete case analysis, and multiple imputation.
result Multiple imputation followed by CART outperformed direct CART with missing data.