English
Related papers

Related papers: Perturbed Double Machine Learning: Nonstandard Inf…

200 papers

Orthogonal statistical learning and double machine learning have emerged as general frameworks for two-stage statistical prediction in the presence of a nuisance component. We establish non-asymptotic bounds on the excess risk of orthogonal…

Machine Learning · Statistics 2022-06-22 Lang Liu , Carlos Cinelli , Zaid Harchaoui

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Machine Learning · Computer Science 2023-10-31 Fady Rezk

Dynamical systems can confront one of two extreme types of disturbances: persistent zero-mean independent noise, and sparse nonzero-mean adversarial attacks, depending on the specific scenario being modeled. While mean-based estimators like…

Optimization and Control · Mathematics 2026-03-31 Jihun Kim , Javad Lavaei

Estimators of doubly robust functionals typically rely on estimating two complex nuisance functions, such as the propensity score and conditional outcome mean for the average treatment effect functional. We consider the problem of how to…

Statistics Theory · Mathematics 2026-03-10 Sean McGrath , Rajarshi Mukherjee

Motivated by data-rich experiments in transcriptional regulation and sensory neuroscience, we consider the following general problem in statistical inference. When exposed to a high-dimensional signal S, a system of interest computes a…

Quantitative Methods · Quantitative Biology 2013-12-16 Justin B. Kinney , Gurinder S. Atwal

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

We consider the problem of inference for projection parameters in linear regression with increasing dimensions. This problem has been studied under a variety of assumptions in the literature. The classical asymptotic normality result for…

Statistics Theory · Mathematics 2024-01-12 Woonyoung Chang , Arun Kumar Kuchibhotla , Alessandro Rinaldo

Data plays a pivotal role in the groundbreaking advancements in artificial intelligence. The quantitative analysis of data significantly contributes to model training, enhancing both the efficiency and quality of data utilization. However,…

Machine Learning · Computer Science 2025-08-21 Haoru Tan , Sitong Wu , Xiuzhe Wu , Wang Wang , Bo Zhao , Zeke Xie , Gui-Song Xia , Xiaojuan Qi

Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident estimates in the context of overparametrized neural networks.…

Machine Learning · Computer Science 2023-05-24 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a general approach to this problem focusing on unsupervised…

Machine Learning · Computer Science 2021-02-22 Andreas Maurer , Daniela A. Parletta , Andrea Paudice , Massimiliano Pontil

The partitioning of data for estimation and calibration critically impacts the performance of propensity score based estimators like inverse probability weighting (IPW) and double/debiased machine learning (DML) frameworks. We extend recent…

Machine Learning · Statistics 2025-05-20 Sven Klaassen , Jan Rabenseifner , Jannis Kueck , Philipp Bach

Despite exceptional predictive performance of Deep sequence models (DSMs), the main concern of their deployment centers around the lack of uncertainty awareness. In contrast, probabilistic models quantify the uncertainty associated with…

Machine Learning · Computer Science 2026-03-03 Wenlong Chen

This paper develops a two-stage method for inference on partially identified parameters in moment inequality models with separable nuisance parameters. In the first stage, the nuisance parameters are estimated separately, and in the second…

Econometrics · Economics 2025-08-28 Xunkang Tian

We introduce a double/debiased machine learning estimator for the impulse response function in settings where a time series of interest is subjected to multiple discrete treatments, assigned over time, which can have a causal effect on…

Econometrics · Economics 2025-12-17 Daniele Ballinari , Alexander Wehrli

This article introduces a new estimator of average treatment effects under unobserved confounding in modern data-rich environments featuring large numbers of units and outcomes. The proposed estimator is doubly robust, combining outcome…

Econometrics · Economics 2024-10-30 Alberto Abadie , Anish Agarwal , Raaz Dwivedi , Abhin Shah

Unmeasured confounding is a key threat to reliable causal inference based on observational studies. Motivated from two powerful natural experiment devices, the instrumental variables and difference-in-differences, we propose a new method…

Methodology · Statistics 2021-11-09 Ting Ye , Ashkan Ertefaie , James Flory , Sean Hennessy , Dylan S. Small

Instrumental variable methods have been widely used to identify causal effects in the presence of unmeasured confounding. A key identification condition known as the exclusion restriction states that the instrument cannot have a direct…

Methodology · Statistics 2022-08-05 Baoluo Sun , Yifan Cui , Eric Tchetgen Tchetgen

This paper develops an asymptotic theory for two-step debiased machine learning (DML) estimators in generalised method of moments (GMM) models with general multiway clustered dependence, without relying on cross-fitting. While cross-fitting…

Econometrics · Economics 2026-04-07 Kaicheng Chen , Harold D. Chiang

Researchers are often interested in learning not only the effect of treatments on outcomes, but also the pathways through which these effects operate. A mediator is a variable that is affected by treatment and subsequently affects outcome.…

Methodology · Statistics 2021-12-22 Jeremiah Jones , Ashkan Ertefaie , Robert L. Strawderman

The existence of label noise imposes significant challenges (e.g., poor generalization) on the training process of deep neural networks (DNN). As a remedy, this paper introduces a permutation layer learning approach termed PermLL to…

Machine Learning · Computer Science 2022-11-30 Salman Alsubaihi , Mohammed Alkhrashi , Raied Aljadaany , Fahad Albalawi , Bernard Ghanem