paper-with-me

Papers

Debiasing Conditional Stochastic Optimization

2023-04-20 · NeurIPS 2023 11 · Lie He, Shiva Prasad Kasiviswanathan

In this paper, we study the conditional stochastic optimization (CSO) problem which covers a variety of applications including portfolio selection, reinforcement learning, robust learning, causal inference, etc. The sample-averaged gradient of the CSO objective is biased due to its nested structure, and therefore requires a high sample complexity for convergence. We introduce a general stochastic extrapolation technique that effectively reduces the bias. We show that for nonconvex smooth objectives, combining this extrapolation with variance reduction techniques can achieve a significantly better sample complexity than the existing bounds. Additionally, we develop new algorithms for the finite-sum variant of the CSO problem that also significantly improve upon existing results. Finally, we believe that our debiasing technique has the potential to be a useful tool for addressing similar challenges in other stochastic optimization problems.

📄 PDF Abstract BibTeX arXiv:2304.10613

Code (0)

등록된 구현이 없습니다.

Tasks

Causal InferenceStochastic Optimization

Similar Papers 제목 키워드 기반

Information-Theoretic Bias Reduction via Causal View of Spurious Correlation

2022-01-10 · Seonguk Seo, Joon-Young Lee, Bohyung Han

We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional…

Face RecognitionFairness

Federated Conditional Stochastic Optimization

2023-10-04 · NeurIPS 2023 11

Conditional stochastic optimization has found applications in a wide range of machine learning tasks, such as invariant learning, AUPRC maximization, and meta-learning. As the demand for training models with large-scale …

Distributed OptimizationFederated LearningMeta-LearningStochastic Optimization

Automatic debiasing of neural networks via moment-constrained learning

2024-09-29 · Christian L. Hines, Oliver J. Hines

Causal and nonparametric estimands in economics and biostatistics can often be viewed as the mean of a linear functional applied to an unknown outcome regression function. Naively learning the regression function and tak…

regression

A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization

2024-05-17 · Andrzej Ruszczyński, Shangzhe Yang

We consider stochastic optimization problems involving an expected value of a nonlinear function of a base random vector and a conditional expectation of another function depending on the base random vector, a dependent …

Stochastic Optimization

StochasticRank: Global Optimization of Scale-Free Discrete Functions

2020-03-04 · ICML 2020 1 · Aleksei Ustimenko, Liudmila Prokhorenkova

In this paper, we introduce a powerful and efficient framework for direct optimization of ranking metrics. The problem is ill-posed due to the discrete structure of the loss, and to deal with that, we introduce two impor…

global-optimizationLearning-To-Rank