Optimization from Structured Samples for Coverage Functions

07/06/2020
by   Wei Chen, et al.
3

We revisit the optimization from samples (OPS) model, which studies the problem of optimizing objective functions directly from the sample data. Previous results showed that we cannot obtain a constant approximation ratio for the maximum coverage problem using polynomially many independent samples of the form {S_i, f(S_i)}_i=1^t (Balkanski et al., 2017), even if coverage functions are (1 - ϵ)-PMAC learnable using these samples (Badanidiyuru et al., 2012), which means most of the function values can be approximately learned very well with high probability. In this work, to circumvent the impossibility result of OPS, we propose a stronger model called optimization from structured samples (OPSS) for coverage functions, where the data samples encode the structural information of the functions. We show that under three general assumptions on the sample distributions, we can design efficient OPSS algorithms that achieve a constant approximation for the maximum coverage problem. We further prove a constant lower bound under these assumptions, which is tight when not considering computational efficiency. Moreover, we also show that if we remove any one of the three assumptions, OPSS for the maximum coverage problem has no constant approximation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/21/2020

Competing Optimally Against An Imperfect Prophet

Consider a gambler who observes the realizations of n independent, non-n...
research
11/06/2017

Prophet Secretary: Surpassing the 1-1/e Barrier

In the Prophet Secretary problem, samples from a known set of probabilit...
research
10/02/2020

Tight Approximation Guarantees for Concave Coverage Problems

In the maximum coverage problem, we are given subsets T_1, …, T_m of a u...
research
03/08/2021

T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP

It is challenging to deal with censored data, where we only have access ...
research
08/17/2023

Polynomial Bounds for Learning Noisy Optical Physical Unclonable Functions and Connections to Learning With Errors

It is shown that a class of optical physical unclonable functions (PUFs)...
research
05/02/2019

Tight Approximation Bounds for Maximum Multi-Coverage

In the classic maximum coverage problem, we are given subsets T_1, ..., ...
research
03/09/2022

Neighborhood persistency of the linear optimization relaxation of integer linear optimization

For an integer linear optimization (ILO) problem, persistency of its lin...

Please sign up or login with your details

Forgot password? Click here to reset