Optimal Approximation -- Smoothness Tradeoffs for Soft-Max Functions
Abstract
A soft-max function has two main efficiency measures: (1) approximation - which corresponds to how well it approximates the maximum function, (2) smoothness - which shows how sensitive it is to changes of its input. Our goal is to identify the optimal approximation-smoothness tradeoffs for different measures of approximation and smoothness. This leads to novel soft-max functions, each of which is optimal for a different application. The most commonly used soft-max function, called exponential mechanism, has optimal tradeoff between approximation measured in terms of expected additive approximation and smoothness measured with respect to R\'enyi Divergence. We introduce a soft-max function, called "piecewise linear soft-max", with optimal tradeoff between approximation, measured in terms of worst-case additive approximation and smoothness, measured with respect to -norm. The worst-case approximation guarantee of the piecewise linear mechanism enforces sparsity in the output of our soft-max function, a property that is known to be important in Machine Learning applications [Martins et al. '16, Laha et al. '18] and is not satisfied by the exponential mechanism. Moreover, the -smoothness is suitable for applications in Mechanism Design and Game Theory where the piecewise linear mechanism outperforms the exponential mechanism. Finally, we investigate another soft-max function, called power mechanism, with optimal tradeoff between expected \textit{multiplicative} approximation and smoothness with respect to the R\'enyi Divergence, which provides improved theoretical and practical results in differentially private submodular optimization.
Cite
@article{arxiv.2010.11450,
title = {Optimal Approximation -- Smoothness Tradeoffs for Soft-Max Functions},
author = {Alessandro Epasto and Mohammad Mahdian and Vahab Mirrokni and Manolis Zampetakis},
journal= {arXiv preprint arXiv:2010.11450},
year = {2026}
}
Comments
Accepted for spotlight presentation at NeurIPS 2020. The updated version fixes a technical gap in the proof of Theorem 4.4