paper-with-me

Papers

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 of the kernel-target alignment with respect to the distribution of training samples over a distributional ball defined by the Kullback-Leibler (KL) divergence. The distributionally robust optimization problem can be recast as a min-max optimization whose objective function includes a log-sum term. We develop a mini-batch biased stochastic primal-dual proximal method to solve the min-max optimization. To debias the minibatch algorithm, we use the Gumbel perturbation technique to estimate the log-sum term. We establish theoretical guarantees for the performance of the proposed multiple kernel learning method. In particular, we prove the consistency, asymptotic normality, stochastic equicontinuity, and the minimax rate of the empirical estimators. In addition, based on the notion of Rademacher and Gaussian complexities, we establish distributionally robust generalization bounds that are tighter than previous known bounds. More specifically, we leverage matrix concentration inequalities to establish distributionally robust generalization bounds. We validate our kernel learning approach for classification with the kernel SVMs on synthetic dataset generated by sampling multvariate Gaussian distributions with differernt variance structures. We also apply our kernel learning approach to the MNIST data-set and evaluate its robustness to perturbation of input images under different adversarial models. More specifically, we examine the robustness of the proposed kernel model selection technique against FGSM, PGM, C\&W, and DDN adversarial perturbations, and compare its performance with alternative state-of-the-art multiple kernel learning paradigms.

📄 PDF Abstract BibTeX arXiv:1902.10365

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsModel SelectionSemantic SegmentationSmall Data Image Classification

Methods 이 논문이 사용한 방법론

PGM A regularization criterion that, differently from dropout and its variants, is deterministic rather than random. It grounds on the…
SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Similar Papers 제목 키워드 기반

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

Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL

2026-05-08 · Shengbo Wang, Zexi Zhang arxiv

Designing model-free algorithms for distributionally robust reinforcement learning (DRRL) poses fundamental challenges. The robust Bellman operator is nonlinear in the transition kernel, which makes one-sample Bellman up…

Reinforcement Learning

A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models

2019-09-25 · Masoud Badiei Khuzani, Liyue Shen, Shahin Shahrampour, Lei Xing

We propose a novel supervised learning method to optimize the kernel in the maximum mean discrepancy generative adversarial networks (MMD GANs), and the kernel support vector machines (SVMs). Specifically, we characteriz…

Two-sample testing

Adversarially Robust Kernel Smoothing

2021-02-16 · Jia-Jie Zhu, Christina Kouridi, Yassine Nemmour, Bernhard Schölkopf

We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization. Our method is motivated by the convex analysis perspective of distributionally robust optimization based on probability …

BIG-bench Machine LearningForm

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…