An Algorithm for Learning Smaller Representations of Models With Scarce Data

10/15/2020
by   Adrian de Wynter, et al.
0

We present a greedy algorithm for solving binary classification problems in situations where the dataset is either too small or not fully representative of the problem being solved, and obtaining more data is not possible. This algorithm is of particular interest when training small models that have trouble generalizing. It relies on a trained model with loose accuracy constraints, an iterative hyperparameter pruning procedure, and a function used to generate new data. Analysis on correctness and runtime complexity under ideal conditions and an extension to deep neural networks is provided. In the former case we obtain an asymptotic bound of O(|Θ^2|(log|Θ| + |θ^2| + T_f(| D|)) + S̅|Θ||E|), where |Θ| is the cardinality of the set of hyperparameters θ to be searched; |E| and |D| are the sizes of the evaluation and training datasets, respectively; S̅ and f̅ are the inference times for the trained model and the candidate model; and T_f(|D|) is a polynomial on |D| and f̅. Under these conditions, this algorithm returns a solution that is 1 ≤ r ≤ 2(1 - 2^-|Θ|) times better than simply enumerating and training with any θ∈Θ. As part of our analysis of the generating function we also prove that, under certain assumptions, if an open cover of D has the same homology as the manifold where the support of the underlying probability distribution lies, then D is learnable, and viceversa.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/16/2021

Neuron-based Pruning of Deep Neural Networks with Better Generalization using Kronecker Factored Curvature Approximation

Existing methods of pruning deep neural networks focus on removing unnec...
research
09/03/2021

Using Topological Framework for the Design of Activation Function and Model Pruning in Deep Neural Networks

Success of deep neural networks in diverse tasks across domains of compu...
research
09/25/2019

A closer look at domain shift for deep learning in histopathology

Domain shift is a significant problem in histopathology. There can be la...
research
08/09/2022

SBPF: Sensitiveness Based Pruning Framework For Convolutional Neural Network On Image Classification

Pruning techniques are used comprehensively to compress convolutional ne...
research
03/13/2020

A Privacy-Preserving DNN Pruning and Mobile Acceleration Framework

To facilitate the deployment of deep neural networks (DNNs) on resource-...
research
06/21/2023

Quantifying lottery tickets under label noise: accuracy, calibration, and complexity

Pruning deep neural networks is a widely used strategy to alleviate the ...
research
11/26/2021

Machine Unlearning: Learning, Polluting, and Unlearning for Spam Email

Machine unlearning for security is studied in this context. Several spam...

Please sign up or login with your details

Forgot password? Click here to reset