English
Related papers

Related papers: Additive Control Variates Dominate Self-Normalisat…

200 papers

If we have an unbiased estimate of some parameter of interest, then its absolute value is positively biased for the absolute value of the parameter. This bias is large when the signal-to-noise ratio (SNR) is small, and it becomes even…

Methodology · Statistics 2020-12-01 Erik van Zwet , Andrew Gelman

Propensity score (PS) weighting methods are often used in non-randomized studies to adjust for confounding and assess treatment effects. The most popular among them, the inverse probability weighting (IPW), assigns weights that are…

Methodology · Statistics 2020-11-04 Yunji Zhou , Roland A. Matsouaka , Laine Thomas

We propose a general framework for regularization in M-estimation problems under time dependent (absolutely regular-mixing) data which encompasses many of the existing estimators. We derive non-asymptotic concentration bounds for the…

Statistics Theory · Mathematics 2018-01-04 Demian Pouzo

We analyze the prediction error of ridge regression in an asymptotic regime where the sample size and dimension go to infinity at a proportional rate. In particular, we consider the role played by the structure of the true regression…

Statistics Theory · Mathematics 2021-03-09 Dominic Richards , Jaouad Mourtada , Lorenzo Rosasco

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Machine Learning · Computer Science 2022-03-08 Aleksander Botev , Matthias Bauer , Soham De

Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline…

Machine Learning · Computer Science 2021-01-01 Thiago D. Simão , Romain Laroche , Rémi Tachet des Combes

The finite sample variance of an inverse propensity weighted estimator is derived in the case of discrete control variables with finite support. The obtained expressions generally corroborate widely-cited asymptotic theory showing that…

Methodology · Statistics 2023-05-19 Andrew Herren , P. Richard Hahn

Many problems involve the use of models which learn probability distributions or incorporate randomness in some way. In such problems, because computing the true expected gradient may be intractable, a gradient estimator is used to update…

Machine Learning · Computer Science 2022-12-29 Ronan Keane , H. Oliver Gao

Anecdotally, using an estimated propensity score is superior to the true propensity score in estimating the average treatment effect based on observational data. However, this claim comes with several qualifications: it holds only if…

Methodology · Statistics 2023-04-03 Fangzhou Su , Wenlong Mou , Peng Ding , Martin J. Wainwright

This paper is concerned with asymptotic theory for penalized spline estimator in bivariate additive model. The focus of this paper is put upon the penalized spline estimator obtained by the backfitting algorithm. The convergence of the…

Statistics Theory · Mathematics 2011-04-28 T. Yoshida , K. Naito

Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the weights for the value function. In this work,…

Machine Learning · Computer Science 2019-11-15 Matthew Schlegel , Wesley Chung , Daniel Graves , Jian Qian , Martha White

We study off-policy evaluation (OPE) from multiple logging policies, each generating a dataset of fixed size, i.e., stratified sampling. Previous work noted that in this setting the ordering of the variances of different importance sampling…

Machine Learning · Computer Science 2020-10-22 Nathan Kallus , Yuta Saito , Masatoshi Uehara

Offline policy optimization could have a large impact on many real-world decision-making problems, as online learning may be infeasible in many applications. Importance sampling and its variants are a commonly used type of estimator in…

Machine Learning · Computer Science 2022-07-05 Yao Liu , Yannis Flet-Berliac , Emma Brunskill

We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes (POMDPs), where the evaluation policy depends only on observable variables and the behavior policy depends on unobservable latent variables. Existing…

Machine Learning · Computer Science 2022-06-17 Chengchun Shi , Masatoshi Uehara , Jiawei Huang , Nan Jiang

Survival outcomes are common in comparative effectiveness studies and require unique handling because they are usually incompletely observed due to right-censoring. A ``once for all'' approach for causal inference with survival outcomes…

Methodology · Statistics 2021-12-21 Shuxi Zeng , Fan Li , Liangyuan Hu , Fan Li

Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present…

Machine Learning · Computer Science 2020-03-06 Arjun Sondhi , David Arbour , Drew Dimmery

Importance sampling (IS) represents a fundamental technique for a large surge of off-policy reinforcement learning approaches. Policy gradient (PG) methods, in particular, significantly benefit from IS, enabling the effective reuse of…

Machine Learning · Computer Science 2024-05-10 Matteo Papini , Giorgio Manganini , Alberto Maria Metelli , Marcello Restelli

In this paper, we address the problem of embedded feature selection for ranking on top of the list problems. We pose this problem as a regularized empirical risk minimization with $p$-norm push loss function ($p=\infty$) and sparsity…

Machine Learning · Computer Science 2012-07-03 Alain Rakotomamonjy

Synthetic control methods (SCMs) are a canonical approach used to estimate treatment effects from panel data in the internet economy. We shed light on a frequently overlooked but ubiquitous assumption made in SCMs of "overlap": a treated…

Econometrics · Economics 2026-02-26 Daniel Ngo , Keegan Harris , Anish Agarwal , Vasilis Syrgkanis , Zhiwei Steven Wu

We study the problem of Safe Policy Improvement (SPI) under constraints in the offline Reinforcement Learning (RL) setting. We consider the scenario where: (i) we have a dataset collected under a known baseline policy, (ii) multiple reward…

Machine Learning · Computer Science 2021-11-01 Harsh Satija , Philip S. Thomas , Joelle Pineau , Romain Laroche
‹ Prev 1 4 5 6 7 8 10 Next ›