IntelligentPooling improves treatment decisions in mHealth.
problem Optimizing treatment decisions in mobile health with limited data and non-stationary responses.
method Generalized Thompson-Sampling bandit algorithms to IntelligentPooling, addressing differential response, limited data, and non-stationary responses.
result IntelligentPooling achieves 26% lower regret compared to state-of-the-art methods.
Proposes a robust Q-learning method to improve treatment strategy estimation.
problem Misspecification of working models in Q-learning leads to confounding and efficiency loss.
method Uses data-adaptive techniques to estimate nuisance parameters robustly.
result Asymptotic behavior of robust Q-learning estimators is studied and shown to be useful.
Estimates RL data for dynamic treatment effects using GMM.
problem Estimating dynamic treatment effects from RL data with nonstationary behavior policies.
method Weighted GMM approach to stabilize variance in adaptive RL settings.
result Valid hypothesis testing and confidence regions for dynamic treatment effects.
Study optimal treatment assignment policies under strategic agent responses.
problem Learning optimal treatment policies with strategic agents complicates estimation.
method Dynamic model with threshold convergence to mean-field equilibrium, consistent estimator for policy gradient.
result Threshold for treatment assignment converges to mean-field equilibrium threshold under large but finite number of agents.
Unified framework for response-adaptive targeting in multi-treatment experiments
problem Improving ethical and statistical efficiency in multi-treatment clinical trials
method Response-adaptive targeting strategies
result Unified framework for α-Rebalancing Targeting Strategies (αRTS) New method estimates treatment effects in complex interference settings.
problem Challenges in estimating treatment effects due to unknown interference.
method Higher-order causal message passing for non-linear feature learning.
result Effective estimation of treatment effect dynamics in complex interference.
The paper explores methods to better estimate treatment effects by leveraging shared structure in potential outcomes.
problem Estimating treatment effects when outcomes may vary widely and existing methods often assume heterogeneity.
method Investigates and compares three learning strategies: regularization, reparametrization, and a multi-task architecture.
result All three approaches improve upon existing baselines, providing insights into their relative strengths.
SODA-RL learns diverse treatment options for hypotension from data.
problem Identifying the best treatment for acute hypotension from observational data.
method SODA-RL: Safely Optimized, Diverse, and Accurate Reinforcement Learning.
result SODA-RL identifies distinct, plausible treatment options from observational data.
New method for robustly estimating treatment effects across different risk levels.
problem Missing risks and tail events in CATE, especially in aggregate analyses.
method Constructing a pseudo-outcome and regressing it on covariates using any regression learner.
result Robust and model-agnostic learning of conditional distributional treatment effects (CDTE).
Estimation of individual treatment effect in observational data is complicated due to the challenges of confounding and selection bias. A useful inferential framework to address this is the counterfactual (potential outcomes) model which takes the hypothetical stance of asking what if an individual had received both tr…
Localized debiased machine learning simplifies estimating quantile treatment effects.
problem Estimating quantile treatment effects in causal inference with many covariates and flexible relationships.
method Localized debiased machine learning (LDML) avoids learning the full nuisance function by estimating only at a single initial guess.
result LDML enables practically-feasible and theoretically-grounded efficient estimation of quantile treatment effects.
Unified treatment of reinforcement learning via convex duality.
problem Applying Fenchel-Rockafellar duality to reinforcement learning.
method Unified derivation of various RL settings using convex duality.
result Ability to perform policy evaluation and on-policy policy gradient with offline data.
Mobile apps and machine learning improve malaria prevention and treatment.
problem High malaria cases and deaths in low-income countries.
method Adaptive interventions using mobile health apps and machine learning.
result Increased malaria testing, adherence, and provider skills.
In many mobile health interventions, treatments should only be delivered in a particular context, for example when a user is currently stressed, walking or sedentary. Even in an optimal context, concerns about user burden can restrict which treatments are sent. To diffuse the treatment delivery over times when a user i…
Study estimates long-term effects of online advertising mechanisms on user behavior and revenue.
problem Estimating long-term treatment effects in online advertising systems.
method Modeling treatment effects as a stopped random walk, using experimental design, and statistical methods.
result Confidence intervals for long-term treatment effects constructed using statistical techniques.
We present examples of agent-based and stochastic models of competition and business processes in economics and finance. We start from as simple as possible models, which have microscopic, agent-based, versions and macroscopic treatment in behavior. Microscopic and macroscopic versions of herding model proposed by Kirm…
We develop a general framework, based on Boltzmann transport theory, to analyze the distribution of wealth in societies. Within this framework we derive the distribution function of wealth by using a two-party trading model for the poor people while for the rich people a new model is proposed where interaction with wea…
From scientific experiments to online A/B testing, the previously observed data often affects how future experiments are performed, which in turn affects which data will be collected. Such adaptivity introduces complex correlations between the data and the collection procedure. In this paper, we prove that when the dat…
There is tremendous interest in precision medicine as a means to improve patient outcomes by tailoring treatment to individual characteristics. An individualized treatment rule formalizes precision medicine as a map from patient information to a recommended treatment. A treatment rule is defined to be optimal if it max…
Proposes a new Alzheimer's disease simulator for causal effect estimation.
problem Lack of suitable benchmarks for evaluating causal effect estimators in real-world healthcare data.
method Developed a simulator of Alzheimer's disease using ADNI dataset, incorporating various parameters to model complexities.
result Compared estimators of average and conditional treatment effects using the new simulator.
This paper presents an analytical treatment of economic systems with an arbitrary number of agents that keeps track of the systems' interactions and agents' complexity. This formalism does not seek to aggregate agents. It rather replaces the standard optimization approach by a probabilistic description of both the enti…
We extend the classic multi-armed bandit (MAB) model to the setting of noncompliance, where the arm pull is a mere instrument and the treatment applied may differ from it, which gives rise to the instrument-armed bandit (IAB) problem. The IAB setting is relevant whenever the experimental units are human since free will…
We use the theory of large deviations to study the pricing of investment-grade tranches of synthetic CDO's. In this paper, we consider a heterogeneous pool of names. Our main tool is a large-deviations analysis which allows us to precisely study the behavior of a large amount of idiosyncratic randomness. Our calculatio…
Paper analyzes blowup of regularized Jang solutions and constant expansion surfaces.
problem Blowup behavior of regularized solutions to Jang equation inside apparent horizons.
method Two geometric treatments: dilation and translation. Characterization of limits of rescaled and translated solutions.
result Limits of properly rescaled solutions are constant expansion surfaces.
The majority of cancer treatments end in failure due to Intra-Tumor Heterogeneity (ITH). ITH in cancer is represented by clonal evolution where different sub-clones compete with each other for resources under conditions of Darwinian natural selection. Predicting the growth of these sub-clones within a tumour is among t…
Paper tackles inconsistent CATE estimation across group assignments.
problem Inconsistent learning behavior for the same instance across different group assignments.
method CLAGA method to eliminate inconsistency.
result Significant performance improvements with CLAGA method.
In this study, we consider an empirical Bayes method for Boltzmann machines and propose an algorithm for it. The empirical Bayes method allows estimation of the values of the hyperparameters of the Boltzmann machine by maximizing a specific likelihood function referred to as the empirical Bayes likelihood function in t…
This paper provides a full controlled version of algebraic K-theory. This includes a rich array of assembly maps; the controlled assembly isomorphism theorem identifying the controlled group with homology; and the stability theorem describing the behavior of the inverse limit as the control parameter goes to 0. There…
Investigates optimal strategies for behavioral control problems with finite variation controls.
problem Behavioral singular stochastic control problems with finite variation controls.
method Abstract framework, applied to storage management and portfolio investment problems, using CPT preferences and Skorokhod representation theorem.
result Existence of optimal strategies for various goal functionals, including CPT preferences.
Transfer learning improves causal model estimates in small samples.
problem Challenges in estimating individual treatment effects (ITE) from small datasets.
method Treatment Agnostic Representation Networks (TARNet) with transfer learning (TL-TARNet).
result Transfer learning reduces ITE error and bias in small samples.
Collectives can manipulate learning platforms by coordinated data submission, requiring strategic assessments and algorithms.
problem Collectives can influence learning platforms by altering data, posing risks and requiring strategic planning.
method Developed a theoretical and algorithmic framework to understand and mitigate collective manipulation of learning platforms.
result Demonstrated the need for strategic assessments and implementable coordination algorithms to prevent collective manipulation.
Study assesses whether RL algorithm personalizes treatment sequences.
problem Evaluate if RL algorithm truly personalizes treatment sequences.
method Resampling-based methodology to investigate personalization.
result RL algorithm's personalization may be due to stochasticity.
We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individ…
Paper develops methods for evaluating mHealth interventions using historical data.
problem Evaluating the long-term effectiveness of mHealth interventions designed for near-term outcomes.
method Develops off-policy estimation techniques to infer long-term average outcomes from historical data.
result Provides estimators and confidence intervals for evaluating mHealth policies.
DTS improves robustness of bandit algorithms in nonstationary environments.
problem Brittle behavior of multi-armed bandit algorithms in nonstationary exogenous factors.
method Deconfounded Thompson Sampling (DTS) that projects population-level performance while controlling for context.
result DTS provides resilience to exogenous variation and balances exploration and exploitation.
We focus on an interpolation method referred to Bayesian reconstruction in this paper. Whereas in standard interpolation methods missing data are interpolated deterministically, in Bayesian reconstruction, missing data are interpolated probabilistically using a Bayesian treatment. In this paper, we address the framewor…
Deconfounding scores improve causal effect estimation with weak overlap.
problem Challenges in causal treatment effect estimation due to weak overlap in high-dimensional data.
method Propose deconfounding scores to preserve identification and target estimation while improving overlap.
result Prognostic scores are overlap-optimal under a broad family of generalized linear models with Gaussian features.
GraphITE estimates individual effects of graph-structured treatments.
problem Estimating individual effects of complex treatment structures.
method Graph neural networks and Hilbert-Schmidt Independence Criterion regularization.
result GraphITE outperforms baselines in estimating treatment effects for large numbers of treatments.
M3E2 neural network estimates multiple treatment effects.
problem Estimating effects of multiple treatments simultaneously.
method Multi-task learning neural network model for multiple treatments, continuous and binary.
result M3E2 outperforms baselines in synthetic datasets.
Proposes a new method to estimate continuous treatment policies and match treatments effectively.
problem Current methods struggle with continuous treatment policies and complex matching.
method Formulates treatment effectiveness as a parametrizable model, using deep learning for optimization.
result Significant improvement in treatment effectiveness and matching efficiency.
Paper tackles efficient evaluation of natural stochastic policies in offline RL.
problem Efficiency issues in evaluating natural stochastic policies due to unknown evaluation policy.
method Derive efficiency bounds for tilting and modified treatment policies, propose nonparametric estimators.
result Proposed estimators attain efficiency bounds under lax conditions and enjoy partial double robustness.
The paper develops methods for causal function estimation and inference with multiway clustered data.
problem Estimation and inference for causal functions under multiway clustering.
method Two-step procedure using machine learning for nuisance parameters and projection onto basis functions.
result Rejects the null hypothesis of uniformly zero effects and reveals heterogeneous treatment effects.
Framework generates personalized insulin treatment strategies using deep models.
problem Developing optimal personalized treatment strategies for diabetes patients.
method Combines deep generative time series models with decision theory.
result Demonstrated improved personalized insulin treatment strategies for diabetes patients.
The self-similar solutions to the mean curvature flows have been defined and studied on the Euclidean space. In this paper we initiate a general treatment of the self-similar solutions to the mean curvature flows on Riemannian cone manifolds. As a typical result we extend the well-known result of Huisken about the asym…
Develops deep jump learning for continuous treatment OPE.
problem Estimating mean outcomes under new treatment rules using historical data from different rules.
method Adaptive deep discretization of continuous treatment space using deep learning and multi-scale change point detection.
result Validated method through theoretical results, simulations, and real application to Warfarin Dosing.
Demand response is designed to motivate electricity customers to modify their loads at critical time periods. The accurate estimation of impact of demand response signals to customers' consumption is central to any successful program. In practice, learning these response is nontrivial because operators can only send a …
New algorithm balances personalization and statistical validity in MRTs.
problem Optimizing decisions in nonstationary settings with habituation and recovery.
method ROGUE-TS Thompson Sampling with probability clipping.
result Achieves lower regret and maintains high statistical power.
Method controls treatment risk in learning beneficial allocations.
problem Learning beneficial treatment allocations with risk control in precision medicine.
method Proposes a certifiable learning method that controls treatment risk with finite samples in the partially identified setting.
result Illustrates method using both simulated and real data.