Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference

Horst Bischof, Wangmeng Zuo, Xi Peng, Danil Prokhorov

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Model optimization and statistical inference have played a central role in various applications of computational intelligence, data analytics, and computer vision. Traditional approaches are usually based on model-centric learning. That is, even after model training, it is still required to design proper algorithms and to specify hand-crafted parameters for optimization and inference. Recently, discriminative learning has demonstrated its power for process-centric learning. Taking domain expertise and problem structure into account, problem-specific deep architectures can be formed by unfolding the model inference as an iterative process, and the parameters of the optimization process can then be learned from training data. These solutions are closely related with bilevel optimization, partial differential equation (PDE), as well as meta learning, and can provide new insights into the studies of versatile statistical and …
Original languageEnglish
Title of host publicationIEEE Transactions on Neural Networks and Learning Systems
Pages2894-2897
Publication statusPublished - 2019

Fingerprint

Computer vision
Partial differential equations
Artificial intelligence

Cite this

Bischof, H., Zuo, W., Peng, X., & Prokhorov, D. (2019). Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference. In IEEE Transactions on Neural Networks and Learning Systems (pp. 2894-2897)

Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference. / Bischof, Horst; Zuo, Wangmeng; Peng, Xi; Prokhorov, Danil.

IEEE Transactions on Neural Networks and Learning Systems. 2019. p. 2894-2897.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Bischof, H, Zuo, W, Peng, X & Prokhorov, D 2019, Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference. in IEEE Transactions on Neural Networks and Learning Systems. pp. 2894-2897.
Bischof H, Zuo W, Peng X, Prokhorov D. Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference. In IEEE Transactions on Neural Networks and Learning Systems. 2019. p. 2894-2897
Bischof, Horst ; Zuo, Wangmeng ; Peng, Xi ; Prokhorov, Danil. / Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference. IEEE Transactions on Neural Networks and Learning Systems. 2019. pp. 2894-2897
@inproceedings{4184c7dd09ab4886bbebc9bb0b9bd106,
title = "Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference",
abstract = "Model optimization and statistical inference have played a central role in various applications of computational intelligence, data analytics, and computer vision. Traditional approaches are usually based on model-centric learning. That is, even after model training, it is still required to design proper algorithms and to specify hand-crafted parameters for optimization and inference. Recently, discriminative learning has demonstrated its power for process-centric learning. Taking domain expertise and problem structure into account, problem-specific deep architectures can be formed by unfolding the model inference as an iterative process, and the parameters of the optimization process can then be learned from training data. These solutions are closely related with bilevel optimization, partial differential equation (PDE), as well as meta learning, and can provide new insights into the studies of versatile statistical and …",
author = "Horst Bischof and Wangmeng Zuo and Xi Peng and Danil Prokhorov",
year = "2019",
language = "English",
pages = "2894--2897",
booktitle = "IEEE Transactions on Neural Networks and Learning Systems",

}

TY - GEN

T1 - Guest Editorial Special Issue on Discriminative Learning for Model Optimization and Statistical Inference

AU - Bischof, Horst

AU - Zuo, Wangmeng

AU - Peng, Xi

AU - Prokhorov, Danil

PY - 2019

Y1 - 2019

N2 - Model optimization and statistical inference have played a central role in various applications of computational intelligence, data analytics, and computer vision. Traditional approaches are usually based on model-centric learning. That is, even after model training, it is still required to design proper algorithms and to specify hand-crafted parameters for optimization and inference. Recently, discriminative learning has demonstrated its power for process-centric learning. Taking domain expertise and problem structure into account, problem-specific deep architectures can be formed by unfolding the model inference as an iterative process, and the parameters of the optimization process can then be learned from training data. These solutions are closely related with bilevel optimization, partial differential equation (PDE), as well as meta learning, and can provide new insights into the studies of versatile statistical and …

AB - Model optimization and statistical inference have played a central role in various applications of computational intelligence, data analytics, and computer vision. Traditional approaches are usually based on model-centric learning. That is, even after model training, it is still required to design proper algorithms and to specify hand-crafted parameters for optimization and inference. Recently, discriminative learning has demonstrated its power for process-centric learning. Taking domain expertise and problem structure into account, problem-specific deep architectures can be formed by unfolding the model inference as an iterative process, and the parameters of the optimization process can then be learned from training data. These solutions are closely related with bilevel optimization, partial differential equation (PDE), as well as meta learning, and can provide new insights into the studies of versatile statistical and …

M3 - Conference contribution

SP - 2894

EP - 2897

BT - IEEE Transactions on Neural Networks and Learning Systems

ER -