Stochastic Maximum Likelihood Optimization via Hypernetworks

12/04/2017
by   Abdul-Saboor Sheikh, et al.
Zalando
IEEE
0

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelihood of target variables given input. Using this approach we obtain competitive empirical results on regression and classification benchmarks.

READ FULL TEXT
06/18/2021

On the benefits of maximum likelihood estimation for Regression and Forecasting

We advocate for a practical Maximum Likelihood Estimation (MLE) approach...
07/25/2022

Maximum Likelihood Ridge Regression

My first paper exclusively about ridge regression was published in Techn...
02/24/2021

Maximum Likelihood Constraint Inference from Stochastic Demonstrations

When an expert operates a perilous dynamic system, ideal constraint info...
08/28/2013

Bayesian Conditional Gaussian Network Classifiers with Applications to Mass Spectra Classification

Classifiers based on probabilistic graphical models are very effective. ...
02/03/2021

SiML: Sieved Maximum Likelihood for Array Signal Processing

Stochastic Maximum Likelihood (SML) is a popular direction of arrival (D...
02/24/2021

A statistical theory of out-of-distribution detection

We introduce a principled approach to detecting out-of-distribution (OOD...

Please sign up or login with your details

Forgot password? Click here to reset