Orthogonal Statistical Learning

• URL: http://arxiv.org/abs/1901.09036v4
• Date: Tue, 6 Jun 2023 01:44:42 GMT
• Title: Orthogonal Statistical Learning
• Authors: Dylan J. Foster and Vasilis Syrgkanis
• Abstract summary: We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk depends on an unknown nuisance parameter. We show that if the population risk satisfies a condition called Neymanity, the impact of the nuisance estimation error on the excess risk bound achieved by the meta-algorithm is of second order.
• Score: 49.55515683387805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We provide non-asymptotic excess risk guarantees for statistical learning in a setting where the population risk with respect to which we evaluate the target parameter depends on an unknown nuisance parameter that must be estimated from data. We analyze a two-stage sample splitting meta-algorithm that takes as input arbitrary estimation algorithms for the target parameter and nuisance parameter. We show that if the population risk satisfies a condition called Neyman orthogonality, the impact of the nuisance estimation error on the excess risk bound achieved by the meta-algorithm is of second order. Our theorem is agnostic to the particular algorithms used for the target and nuisance and only makes an assumption on their individual performance. This enables the use of a plethora of existing results from machine learning to give new guarantees for learning with a nuisance component. Moreover, by focusing on excess risk rather than parameter estimation, we can provide rates under weaker assumptions than in previous works and accommodate settings in which the target parameter belongs to a complex nonparametric class. We provide conditions on the metric entropy of the nuisance and target classes such that oracle rates of the same order as if we knew the nuisance parameter are achieved.

Related papers

• Information-Theoretic Safe Bayesian Optimization [59.758009422067005]
  We consider a sequential decision making task, where the goal is to optimize an unknown function without evaluating parameters that violate an unknown (safety) constraint. Most current methods rely on a discretization of the domain and cannot be directly extended to the continuous case. We propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate.
  arXiv  Detail & Related papers  (2024-02-23T14:31:10Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Optimal estimation of pure states with displaced-null measurements [0.0]
  We revisit the problem of estimating an unknown parameter of a pure quantum state. We investigate null-measurement' strategies in which the experimenter aims to measure in a basis that contains a vector close to the true system state.
  arXiv  Detail & Related papers  (2023-10-10T16:46:24Z)
• Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters [1.5999407512883512]
  We propose a novel method named emph kernel plug-in estimation (KDPE) We show that KDPE simultaneously debiases emphall pathwise differentiable target parameters that satisfy our regularity conditions. We numerically illustrate the use of KDPE and validate our theoretical results.
  arXiv  Detail & Related papers  (2023-06-14T15:58:50Z)
• A Tale of Sampling and Estimation in Discounted Reinforcement Learning [50.43256303670011]
  We present a minimax lower bound on the discounted mean estimation problem. We show that estimating the mean by directly sampling from the discounted kernel of the Markov process brings compelling statistical properties.
  arXiv  Detail & Related papers  (2023-04-11T09:13:17Z)
• Mitigating multiple descents: A model-agnostic framework for risk monotonization [84.6382406922369]
  We develop a general framework for risk monotonization based on cross-validation. We propose two data-driven methodologies, namely zero- and one-step, that are akin to bagging and boosting.
  arXiv  Detail & Related papers  (2022-05-25T17:41:40Z)
• Partial Identification with Noisy Covariates: A Robust Optimization Approach [94.10051154390237]
  Causal inference from observational datasets often relies on measuring and adjusting for covariates. We show that this robust optimization approach can extend a wide range of causal adjustment methods to perform partial identification. Across synthetic and real datasets, we find that this approach provides ATE bounds with a higher coverage probability than existing methods.
  arXiv  Detail & Related papers  (2022-02-22T04:24:26Z)
• Nonparametric Estimation of Uncertainty Sets for Robust Optimization [2.741266294612776]
  We investigate a data-driven approach to constructing uncertainty sets for robust optimization problems. We provide a nonparametric method to estimate uncertainty sets whose probability mass is guaranteed to approximate a given target mass.
  arXiv  Detail & Related papers  (2020-04-07T01:47:55Z)
• Selective machine learning of doubly robust functionals [6.880360838661036]
  We propose a selective machine learning framework for making inferences about a finite-dimensional functional defined on a semiparametric model. We introduce a new selection criterion aimed at bias reduction in estimating the functional of interest based on a novel definition of pseudo-risk.
  arXiv  Detail & Related papers  (2019-11-05T19:00:03Z)

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.