Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion

• URL: http://arxiv.org/abs/2605.30319v1
• Date: Thu, 28 May 2026 17:55:23 GMT
• Title: Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
• Abstract summary: Estimating heterogeneous treatment effects can then be expressed as obtaining a good estimation of each row's average in this matrix.<n>We give a simple, computationally efficient estimator without knowledge of the propensities and under standard low-rankness and regularity assumptions.<n>Technically, our analysis establishes the first sharp row-wise $ell$-perturbation bound for low-rank approximation.
• Score: 8.03845232151202
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A central goal of modern causal inference is estimating heterogeneous treatment effects to answer questions like "how does an intervention affect each unit," rather than only on average. We study this problem with panel-data where we observe $n$ units across $m$ times under unknown, non-uniform treatment assignments. The data in this setting is naturally represented as a matrix of all unit--time treatment effects. Estimating heterogeneous treatment effects can then be expressed as obtaining a good estimation of each row's average in this matrix. This allows us to formulate the problem as matrix completion, which can be solved under natural low-rankness assumptions. However, existing matrix-completion guarantees are not powerful enough to get meaningful bounds for the per-row guarantee required for estimating the heterogeneous treatment effect; roughly speaking, they are only useful for estimating average treatment effect bounds, as also illustrated in a recent line of work. We give a simple, computationally efficient estimator that, without knowledge of the propensities and under standard low-rankness and regularity assumptions, achieves a row-wise $\ell_2$ error of $\tilde{O}(\sqrt{\frac{1}{n} + \frac{n}{m^2}})$. Technically, our analysis establishes the first sharp row-wise $\ell_2$-perturbation bound for low-rank approximation, complementing existing spectral-, Frobenius-, and entrywise perturbation theory.

Related papers

• Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements [66.94250413799232]
  We study mean estimation of a random vector $X$ in a distributed parameter-server-worker setup.<n>Key challenges are adversarial measurements and asynchrony.<n>Results provide a unified finite-time characterization of robustness, identifiability, and statistical efficiency in distributed linear estimation with adversarial workers.
  arXiv  Detail & Related papers  (2026-04-07T11:45:55Z)
• Almost Asymptotically Optimal Active Clustering Through Pairwise Observations [59.20614082241528]
  We propose a new analysis framework for clustering $M$ items into an unknown number of $K$ distinct groups using noisy and actively collected responses.<n>We establish a fundamental lower bound on the expected number of queries needed to achieve a desired confidence in the accuracy of the clustering.<n>We develop a computationally feasible variant of the Generalized Likelihood Ratio statistic and show that its performance gap to the lower bound can be accurately empirically estimated.
  arXiv  Detail & Related papers  (2026-02-05T14:16:47Z)
• Cross-World Assumption and Refining Prediction Intervals for Individual Treatment Effects [6.083038976289835]
  For high-stakes decision-making, individual treatment effect estimates must be accompanied by valid prediction intervals.<n>For high-stakes decision-making, individual treatment effect estimates must be accompanied by valid prediction intervals.
  arXiv  Detail & Related papers  (2025-07-16T18:58:18Z)
• It's Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation [34.755498967191535]
  We study how well one can estimate a treatment effect given black-box machine learning estimates of nuisance functions.<n>We find that the answer depends in a surprising way on the distribution of the treatment noise.
  arXiv  Detail & Related papers  (2025-07-03T03:31:45Z)
• Orthogonal Causal Calibration [55.28164682911196]
  We develop general algorithms for reducing the task of causal calibration to that of calibrating a standard (non-causal) predictive model.<n>Our results are exceedingly general, showing that essentially any existing calibration algorithm can be used in causal settings.
  arXiv  Detail & Related papers  (2024-06-04T03:35:25Z)
• Sparse PCA with Oracle Property [115.72363972222622]
  We propose a family of estimators based on the semidefinite relaxation of sparse PCA with novel regularizations. We prove that, another estimator within the family achieves a sharper statistical rate of convergence than the standard semidefinite relaxation of sparse PCA.
  arXiv  Detail & Related papers  (2023-12-28T02:52:54Z)
• Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency [59.48096489854697]
  The problem of estimating a linear functional based on observational data is canonical in both the causal inference and bandit literatures. We prove non-asymptotic upper bounds on the mean-squared error of such procedures. We establish its instance-dependent optimality in finite samples via matching non-asymptotic local minimax lower bounds.
  arXiv  Detail & Related papers  (2022-09-26T23:50:55Z)
• A General Framework for Treatment Effect Estimation in Semi-Supervised and High Dimensional Settings [0.0]
  We develop a family of SS estimators which are more robust and (2) more efficient than their supervised counterparts. We further establish root-n consistency and normality of our SS estimators whenever the propensity score in the model is correctly specified. Our estimators are shown to be semi-parametrically efficient as long as all the nuisance functions are correctly specified.
  arXiv  Detail & Related papers  (2022-01-03T04:12:44Z)
• Leveraged Matrix Completion with Noise [84.20092979053119]
  We show that we can provably recover an unknown $ntimes n$ matrix of rank $r$ from just about $mathcalO(nrlog2 (n))$ entries. Our proofs are supported by a novel approach that phrases sufficient optimality conditions based on the Golfing Scheme.
  arXiv  Detail & Related papers  (2020-11-11T16:25:45Z)
• High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation [0.0]
  The estimation of causal treatment effects from observational data is a fundamental problem in causal inference. We propose a common objective function involving outcomes across treatment cohorts. We validate our approach with experiments on treatment effect estimation.
  arXiv  Detail & Related papers  (2020-11-03T19:54:16Z)
• A Scalable, Adaptive and Sound Nonconvex Regularizer for Low-rank Matrix Completion [60.52730146391456]
  We propose a new non scalable low-rank regularizer called "nuclear Frobenius norm" regularizer, which is adaptive and sound. It bypasses the computation of singular values and allows fast optimization by algorithms. It obtains state-of-the-art recovery performance while being the fastest in existing matrix learning methods.
  arXiv  Detail & Related papers  (2020-08-14T18:47:58Z)
• Median Matrix Completion: from Embarrassment to Optimality [16.667260586938234]
  We consider matrix completion with absolute deviation loss and obtain an estimator of the median matrix. Despite several appealing properties of median, the non-smooth absolute deviation loss leads to computational challenge. We propose a novel refinement step, which turns such inefficient estimators into a rate (near-optimal) matrix completion procedure.
  arXiv  Detail & Related papers  (2020-06-18T10:01:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.