arXiv research

Bounds and sensitivity analysis for causal effects with MNAR confounders.

The paper bounds and identifies joint probabilities in causal inference with monotonicity assumptions.

Develops conformalized prediction intervals for bounded continuous outcomes.

Estimation of individual treatment effects is commonly used as the basis for contextual decision making in fields such as healthcare, education, and economics. However, it is often sufficient for the decision maker to have estimates of upper and lower bounds on the potential outcomes of decision alternatives to assess …

Study optimizes identifying the best arm with fixed rounds and Gaussian outcomes.

Proposes a new model to identify unknown counterfactual outcomes for continuous variables.

The paper introduces metrics to rank potential outcomes for better decision-making.

Bounds on treatment effect sensitivity in causal reasoning using Hölder's inequality.

Study uses surrogate data to improve treatment effect estimation with scarce outcome data.

New algorithm bounds regret in mediator feedback bandit problems.

A new Thompson Sampling framework handles uncertainty by imputing missing data.

This paper identifies and bounds ICE central moments using PO marginal central moments.

PROWL uses robust reward estimates to improve ITR selection.

New algorithm for maximizing revenue in multinomial logistic bandits.

Proposes a method to improve CATE estimation by imputing missing potential outcomes.

Optimal strategy identified for minimizing regret in fixed-budget best arm selection.

A new method removes biases in data integration by using surrogate control outcomes.

Paper proposes a method to model health outcomes using varying-coefficients and KNN-based LASSO.

We present a new machine learning approach to estimate personalized treatment effects in the classical potential outcomes framework with binary outcomes. To overcome the problem that both treatment and control outcomes for the same unit are required for supervised learning, we propose surrogate loss functions that inco…

Develops new methods to estimate treatment effects in survival data with competing risks.

DCMA uses generative models to analyze treatment effects on entire outcome distributions.

DCMA uses generative models to analyze complex treatment effects on outcome distributions.

We consider the problem of sequential sampling from a finite number of independent statistical populations to maximize the expected infinite horizon average outcome per period, under a constraint that the expected average sampling cost does not exceed an upper bound. The outcome distributions are not known. We construc…

Estimates counterfactual outcomes linking observed and unobserved data.

Wasserstein Policy Learning for Distributional Outcomes

DFL framework improves action and outcome fairness in policy learning.

New algorithms handle missing outcomes in MAB, reducing regret.

PGAE uses predictions to guide active experimentation.

Motivated by problems in search and detection we present a solution to a Combinatorial Multi-Armed Bandit (CMAB) problem with both heavy-tailed reward distributions and a new class of feedback, filtered semibandit feedback. In a CMAB problem an agent pulls a combination of arms from a set $\{1,...,k\}$ in each round, g…

We demonstrate that, in the classical non-stochastic regret minimization problem with $d$ decisions, gains and losses to be respectively maximized or minimized are fundamentally different. Indeed, by considering the additional sparsity assumption (at each stage, at most $s$ decisions incur a nonzero outcome), we derive…

New algorithm reduces semi-bandit regret using covariance estimates.

A new multi-armed bandit framework with credal sets for uncertain outcomes.

In principal-agent models, a principal offers a contract to an agent to perform a certain task. The agent exerts a level of effort that maximizes her utility. The principal is oblivious to the agent's chosen level of effort, and conditions her wage only on possible outcomes. In this work, we consider a model in which t…

New framework for estimating treatment effects in observational studies.

We consider the problem of sequential learning from categorical observations bounded in [0,1]. We establish an ordering between the Dirichlet posterior over categorical outcomes and a Gaussian posterior under observations with N(0,1) noise. We establish that, conditioned upon identical data with at least two observatio…

Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner suffers a loss and receives a feedback signal. The goal of the learner is to mi…

Unified multitask learning framework for mixed-type outcomes.

A new DP algorithm for weighted ERM protects sensitive data in predictive models.

We consider the linear contextual bandit problem with resource consumption, in addition to reward generation. In each round, the outcome of pulling an arm is a reward as well as a vector of resource consumptions. The expected values of these outcomes depend linearly on the context of that arm. The budget/capacity const…

The paper develops a method to learn robust decision policies from observational data, reducing high-cost outcomes.

ADIGen: Automatic, Debiased, and Invariant Counterfactual Generation

Approach collects missing outcomes to improve fairness in classification.

New method improves mHealth user engagement using Thompson sampling for count data.

We analyze the regret of combinatorial Thompson sampling (CTS) for the combinatorial multi-armed bandit with probabilistically triggered arms under the semi-bandit feedback setting. We assume that the learner has access to an exact optimization oracle but does not know the expected base arm outcomes beforehand. When th…

Categorical distributions are ubiquitous in machine learning, e.g., in classification, language models, and recommendation systems. However, when the number of possible outcomes is very large, using categorical distributions becomes computationally expensive, as the complexity scales linearly with the number of outcome…

New method improves counterfactual distribution learning for high-dimensional outcomes.

New algorithm identifies best intervention without graph knowledge.

We provide a simple and efficient algorithm for adversarial $k$-action $d$-outcome non-degenerate locally observable partial monitoring game for which the $n$-round minimax regret is bounded by $6(d+1) k^{3/2} \sqrt{n \log(k)}$, matching the best known information-theoretic upper bound. The same algorithm also achieves…