Log In Sign Up

An Approximation Algorithm for Optimal Subarchitecture Extraction

by   Adrian de Wynter, et al.

We consider the problem of finding the set of architectural parameters for a chosen deep neural network which is optimal under three metrics: parameter size, inference speed, and error rate. In this paper we state the problem formally, and present an approximation algorithm that, for a large subset of instances behaves like an FPTAS with an approximation error of ρ≤ |1- ϵ|, and that runs in O(|Ξ| + |W^*_T|(1 + |Θ||B||Ξ|/(ϵ s^3/2))) steps, where ϵ and s are input parameters; |B| is the batch size; |W^*_T| denotes the cardinality of the largest weight set assignment; and |Ξ| and |Θ| are the cardinalities of the candidate architecture and hyperparameter spaces, respectively.


page 1

page 2

page 3

page 4


On ultrametric 1-median selection

Consider the problem of finding a point in an ultrametric space with the...

An Efficient Approximation Algorithm for Point Pattern Matching Under Noise

Point pattern matching problems are of fundamental importance in various...

Almost Optimal Semi-streaming Maximization for k-Extendible Systems

In this paper we consider the problem of finding a maximum weight set su...

A 3-Approximation Algorithm for a Particular Case of the Hamiltonian p-Median Problem

Given a weighted graph G with n vertices and m edges, and a positive int...

Breaking O(nr) for Matroid Intersection

We present algorithms that break the Õ(nr)-independence-query bound for ...

On the Complexity of BWT-runs Minimization via Alphabet Reordering

We present the first set of results on the computational complexity of m...

Election with Bribed Voter Uncertainty: Hardness and Approximation Algorithm

Bribery in election (or computational social choice in general) is an im...