Can We Do Better Than Random Start? The Power of Data Outsourcing

05/17/2022
by   Yi Chen, et al.
0

Many organizations have access to abundant data but lack the computational power to process the data. While they can outsource the computational task to other facilities, there are various constraints on the amount of data that can be shared. It is natural to ask what can data outsourcing accomplish under such constraints. We address this question from a machine learning perspective. When training a model with optimization algorithms, the quality of the results often relies heavily on the points where the algorithms are initialized. Random start is one of the most popular methods to tackle this issue, but it can be computationally expensive and not feasible for organizations lacking computing resources. Based on three different scenarios, we propose simulation-based algorithms that can utilize a small amount of outsourced data to find good initial points accordingly. Under suitable regularity conditions, we provide theoretical guarantees showing the algorithms can find good initial points with high probability. We also conduct numerical experiments to demonstrate that our algorithms perform significantly better than the random start approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/27/2014

Sensitivity Analysis for Computationally Expensive Models using Optimization and Objective-oriented Surrogate Approximations

In this paper, we focus on developing efficient sensitivity analysis met...
research
05/29/2016

TripleSpin - a generic compact paradigm for fast machine learning computations

We present a generic compact computational framework relying on structur...
research
09/07/2023

A computationally lightweight safe learning algorithm

Safety is an essential asset when learning control policies for physical...
research
07/12/2019

A machine learning framework for computationally expensive transient models

The promise of machine learning has been explored in a variety of scient...
research
03/11/2022

Randomized quasi-optimal local approximation spaces in time

We target time-dependent partial differential equations (PDEs) with coef...
research
08/29/2022

On the reconstruction of functions from values at subsampled quadrature points

This paper is concerned with function reconstruction from samples. The s...
research
12/27/2021

Implicit regularity and linear convergence rates for the generalized trust-region subproblem

In this paper we develop efficient first-order algorithms for the genera...

Please sign up or login with your details

Forgot password? Click here to reset