Duality for the Adversarial Total Variation
Adversarial training of binary classifiers can be reformulated as regularized risk minimization involving a nonlocal total variation. Building on this perspective, we establish a characterization of the subdifferential of this total variation using duality techniques. To achieve this, we derive a dual representation of the nonlocal total variation and a related integration of parts formula, involving a nonlocal gradient and divergence. We provide such duality statements both in the space of continuous functions vanishing at infinity on proper metric spaces and for the space of essentially bounded functions on Euclidean domains. Furthermore, under some additional conditions we provide characterizations of the subdifferential in these settings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generalized roof duality and bisubmodular functions
Consider a convex relaxation $\hat f$ of a pseudo-boolean function $f$. We say that the relaxation is {\em totally half-integral} if $\hat f(\bx)$ is a polyhedral function with half-integral extreme points $\bx$, and thi…
Denoising of image gradients and total generalized variation denoising
We revisit total variation denoising and study an augmented model where we assume that an estimate of the image gradient is available. We show that this increases the image reconstruction quality and derive that the resu…
DenoisingImage ReconstructionFormulating Beurling LASSO for Source Separation via Proximal Gradient Iteration
Beurling LASSO generalizes the LASSO problem to finite Radon measures regularized via their total variation. Despite its theoretical appeal, this space is hard to parametrize, which poses an algorithmic challenge. We pro…
A Lipschitz spaces view of infinitely wide shallow neural networks
We revisit the mean field parametrization of shallow neural networks, using signed measures on unbounded parameter spaces and duality pairings that take into account the regularity and growth of activation functions. Thi…
Optimal Bounds between f-Divergences and Integral Probability Metrics
The families of f-divergences (e.g. the Kullback-Leibler divergence) and Integral Probability Metrics (e.g. total variation distance or maximum mean discrepancies) are commonly used in optimization and estimation. In thi…
LEMMA