paper-with-me

Papers

Distributionally Robust Optimization and Generalization in Kernel Methods

2019-05-27 · NeurIPS 2019 12 · Matthew Staib, Stefanie Jegelka

Distributionally robust optimization (DRO) has attracted attention in machine learning due to its connections to regularization, generalization, and robustness. Existing work has considered uncertainty sets based on phi-divergences and Wasserstein distances, each of which have drawbacks. In this paper, we study DRO with uncertainty sets measured via maximum mean discrepancy (MMD). We show that MMD DRO is roughly equivalent to regularization by the Hilbert norm and, as a byproduct, reveal deep connections to classic results in statistical learning. In particular, we obtain an alternative proof of a generalization bound for Gaussian kernel ridge regression via a DRO lense. The proof also suggests a new regularizer. Our results apply beyond kernel methods: we derive a generically applicable approximation of MMD DRO, and show that it generalizes recent work on variance-based regularization.

📄 PDF Abstract BibTeX arXiv:1905.10943

Code (1)

mstaib/mmd-dro-code

Similar Papers 제목 키워드 기반

A Distributionally Robust Optimization Method for Adversarial Multiple Kernel Learning

2019-02-27 · Masoud Badiei Khuzani, Hongyi Ren, Md Tauhidul Islam, Lei Xing

We propose a novel data-driven method to learn a mixture of multiple kernels with random features that is certifiabaly robust against adverserial inputs. Specifically, we consider a distributionally robust optimization o…

Generalization BoundsModel SelectionSemantic SegmentationSmall Data Image Classification

Kernel Distributionally Robust Optimization

2020-06-12 · Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf

We propose kernel distributionally robust optimization (Kernel DRO) using insights from the robust optimization theory and functional analysis. Our method uses reproducing kernel Hilbert spaces (RKHS) to construct a wide…

Stochastic Optimization

Distributionally Robust Optimal and Safe Control of Stochastic Systems via Kernel Conditional Mean Embedding

2023-04-02 · Licio Romao, Ashish R. Hota, Alessandro Abate

We present a novel distributionally robust framework for dynamic programming that uses kernel methods to design feedback control policies. Specifically, we leverage kernel mean embedding to map the transition probabiliti…

Distributional Robustness Bounds Generalization Errors

2022-12-20 · Shixiong Wang, Haowei Wang

Bayesian methods, distributionally robust optimization methods, and regularization methods are three pillars of trustworthy machine learning combating distributional uncertainty, e.g., the uncertainty of an empirical dis…

Hedging Complexity in Generalization via a Parametric Distributionally Robust Optimization Framework

2022-12-03 · Garud Iyengar, Henry Lam, Tianyu Wang

Empirical risk minimization (ERM) and distributionally robust optimization (DRO) are popular approaches for solving stochastic optimization problems that appear in operations management and machine learning. Existing gen…

Generalization BoundsManagementPortfolio OptimizationStochastic Optimization