• Corpus ID: 15979219

Proof and Implementation of Algorithmic Realization of Learning Using Privileged Information ( LUPI ) Paradigm : SVM +

@inproceedings{Celik2015ProofAI,
  title={Proof and Implementation of Algorithmic Realization of Learning Using Privileged Information ( LUPI ) Paradigm : SVM +},
  author={Z. Berkay Celik and Rauf Izmailov and Patrick Mcdaniel},
  year={2015}
}
Vapnik et al. recently introduced a new learning paradigm called Learning Using Privileged Information (LUPI). In this paradigm, along with standard training data, the teacher provides the student privileged (additional) information, yet not available at test time. The paradigm is realized by implementation of SVM+ algorithm. In this report, we give the proof of the SVM+ algorithm and show implementation details in MATLAB quadratic programming (quadprog()) function provided by the optimization… 
Extending Detection with Privileged Information via Generalized Distillation
TLDR
The empirical study shows that detection with privileged information via generalized distillation increases precision and recall in systems of user face authentication, fast-flux bot detection, and malware classification over systems with no privileged information.
Braverman Readings in Machine Learning. Key Ideas from Inception to Current State
TLDR
A generalized probabilistic featureless SVM-based approach to combining different data sources via supervised selective kernel fusion with significant qualitative advantages over other methods of kernel fusion on example of membrane protein prediction is demonstrated.
Detection under Privileged Information ( Full Paper ) ∗
For well over a quarter century, detection systems have been driven by models learned from input features collected from real or simulated environments. An artifact (e.g., network event, potential
Feature Cultivation in Privileged Information-augmented Detection
TLDR
Evaluation shows that use of privileged information leads to up to 8.2% relative decrease in detection error for fast-flux bot detection over a system with no privileged information, and 5% for malware classification.
Detection under Privileged Information
TLDR
This paper adapt and extend recent advances in knowledge transfer, model influence, and distillation to enable the use of forensic or other data unavailable at runtime in a range of security domains.
Extending Detection with Forensic Information
TLDR
This paper adapt and extend recent advances in knowledge transfer, model influence, and distillation to enable the use of forensic data in a range of security domains and shows that privileged information increases detection precision and recall over a system with no privileged information.

References

SHOWING 1-9 OF 9 REFERENCES
SMO-Style Algorithms for Learning Using Privileged Information
TLDR
Two new algorithms for solving the optimization problem of SVM+.
A new learning paradigm: Learning using privileged information
TLDR
Details of the new paradigm and corresponding algorithms are discussed, some new algorithms are introduced, several specific forms of privileged information are considered, and superiority of thenew learning paradigm over the classical learning paradigm when solving practical problems is demonstrated.
Learning with Intelligent Teacher: Similarity Control and Knowledge Transfer - In memory of Alexey Chervonenkis
TLDR
Two mechanisms that can be used for significantly accelerating the speed of Student's training are described: correction of Student’s concepts of similarity between examples, and direct Teacher-Student knowledge transfer.
Mind the Nuisance: Gaussian Process Classification using Privileged Noise
TLDR
It is shown that privileged information can naturally be treated as noise in the latent function of a Gaussian process classifier (GPC), and that advanced neural networks and deep learning methods can be compressed as privileged information.
Learning to Rank Using Privileged Information
TLDR
This work introduces two maximum-margin techniques that are able to make use of this additional source of information about the training data which however will not be available at test time, and shows that the framework is applicable to several scenarios that have been studied in computer vision before.
Unifying distillation and privileged information
TLDR
The theoretical and causal insight about the inner workings of generalized distillation is provided, it is extended to unsupervised, semisupervised and multitask learning scenarios, and its efficacy on a variety of numerical simulations on both synthetic and real-world data is illustrated.
Distilling the Knowledge in a Neural Network
TLDR
This work shows that it can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model and introduces a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse.
Privileged information-based conditional regression forest for facial feature detection
  • Heng Yang, I. Patras
  • Mathematics, Computer Science
    2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)
  • 2013
TLDR
A method that utilises privileged information, that is information that is available only at the training phase, in order to train Regression Forests for facial feature detection by choosing the split functions at some randomly chose internal tree nodes according to the information gain calculated from the privileged information.
MATLAB documentation of quadprog
  • MATLAB documentation of quadprog
  • 2015