Search Results for author:
Found 27 papers, 7 papers with code
Can We Validate Counterfactual Estimations in the Presence of General Network Interference?
In experimental settings with network interference, a unit's treatment can influence outcomes of other units, challenging both causal effect estimation and its validation.
Post Launch Evaluation of Policies in a High-Dimensional Setting
To address this, we propose a two-phase approach: first using nearest neighbor matching based on unit covariates to select similar control units, then applying supervised learning methods suitable for high-dimensional data to estimate counterfactual outcomes.
Higher-Order Causal Message Passing for Experimentation with Complex Interference
Our estimator draws on information from the sample mean and variance of unit outcomes and treatments over time, enabling efficient use of observed data to estimate the evolution of the system state.
Aligning Model Properties via Conformal Risk Control
Specifically, we develop a general procedure for converting queries for testing a given property $\mathcal{P}$ to a collection of loss functions suitable for use in a conformal risk control algorithm.
A Probabilistic Approach for Model Alignment with Human Comparisons
The two-stage framework first learns low-dimensional representations from noisy-labeled data via an SL procedure and then uses human comparisons to improve the model alignment.
Causal Message Passing for Experiments with Unknown and General Network Interference
It is tailored for multi-period experiments and is particularly effective in settings with many units and prevalent network interference.
Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits
This methodology enables us to formulate an instance-dependent frequentist regret bound, which incorporates the geometric information, for a broad class of base algorithms, including Greedy, OFUL, and Thompson sampling.
Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms
Next, we design two-phase bandit algorithms that first use subsampling and low-rank matrix estimation to obtain a substantially smaller targeted set of products and then apply a UCB procedure on the target products to find the best one.
Thompson Sampling Efficiently Learns to Control Diffusion Processes
To the best of our knowledge, this is the first such result for Thompson sampling in a diffusion process control problem.
Learning to Recommend Using Non-Uniform Data
Utilizing this observation, we introduce a new optimization problem to select a weight matrix that minimizes the upper bound on the prediction error.
The Elliptical Potential Lemma for General Distributions with an Application to Linear Thompson Sampling
The elliptical potential lemma is a key tool for quantifying uncertainty in estimating parameters of the reward function, but it requires the noise and the prior distributions to be Gaussian.
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms
We study the structure of regret-minimizing policies in the {\em many-armed} Bayesian multi-armed bandit problem: in particular, with $k$ the number of arms and $T$ the time horizon, we consider the case where $k \geq \sqrt{T}$.
On Frequentist Regret of Linear Thompson Sampling
This paper studies the stochastic linear bandit problem, where a decision-maker chooses actions from possibly time-dependent sets of vectors in $\mathbb{R}^d$ and receives noisy rewards.
Recommendation on a Budget: Column Space Recovery from Partially Observed Entries with Random or Active Sampling
We analyze alternating minimization for column space recovery of a partially observed, approximately low rank matrix with a growing number of columns and a fixed budget of observations per column.
The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms
This finding diverges from the notion of free exploration, which relates to covariate variation, as recently discussed in contextual bandit literature.
A General Theory of the Stochastic Linear Bandit and Its Applications
First, our new notion of optimism in expectation gives rise to a new algorithm, called sieved greedy (SG) that reduces the overexploration problem in OFUL.
Personalizing Many Decisions with High-Dimensional Covariates
We consider the k-armed stochastic contextual bandit problem with d dimensional features, when both k and d can be large.
Optimal Experimental Design for Staggered Rollouts
Next, we study an adaptive experimental design problem, where both the decision to continue the experiment and treatment assignment decisions are updated after each period's data is collected.
On Low-rank Trace Regression under General Sampling Distribution
In this paper, we study the trace regression when a matrix of parameters B* is estimated via the convex relaxation of a rank-regularized regression or via regularized non-convex optimization.
Ensemble Methods for Causal Effects in Panel Data Settings
This paper studies a panel data setting where the goal is to estimate causal effects of an intervention by predicting the counterfactual values of outcomes for treated units, had they not received the treatment.
Matrix Completion Methods for Causal Panel Data Models
In this paper we study methods for estimating causal effects in settings with panel data, where some units are exposed to a treatment during some periods and the goal is estimating counterfactual (untreated) outcomes for the treated unit/period combinations.
Statistics Theory Econometrics Statistics Theory
Mostly Exploration-Free Algorithms for Contextual Bandits
We prove that this algorithm is rate optimal without any additional assumptions on the context distribution or the number of arms.
Scaled Least Squares Estimator for GLMs in Large-Scale Problems
We study the problem of efficiently estimating the coefficients of generalized linear models (GLMs) in the large-scale setting where the number of observations $n$ is much larger than the number of predictors $p$, i. e. $n\gg p \gg 1$.
Scalable Approximations for Generalized Linear Problems
Using this relation, we design an algorithm that achieves the same accuracy as the empirical risk minimizer through iterations that attain up to a cubic convergence rate, and that are cheaper than any batch optimization algorithm by at least a factor of $\mathcal{O}(p)$.
Dynamic Pricing with Demand Covariates
In particular, we assume that the firm knows the expected demand under a particular price from historical data, and in each period, before setting the price, the firm has access to extra information (demand covariates) which may be predictive of the demand.
Estimating LASSO Risk and Noise Level
In this context, we develop new estimators for the $\ell_2$ estimation risk $\|\hat{\theta}-\theta_0\|_2$ and the variance of the noise.
The LASSO risk: asymptotic results and real world examples
We consider the problem of learning a coefficient vector x0 from noisy linear observation y=Ax0+w.
