Concept

Margin (machine learning)

Related publications (10)

Deep Learning Theory Through the Lens of Diagonal Linear Networks

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Error scaling laws for kernel classification under source and capacity conditions

Florent Gérard Krzakala, Lenka Zdeborová, Hugo Chao Cui, Bruno Loureiro

In this manuscript we consider the problem of kernel classification. While worst-case bounds on the decay rate of the prediction error with the number of samples are known for some classifiers, they often fail to accurately describe the learning curves of ...

2023

Understanding and Improving Fast Adversarial Training

Nicolas Henri Bernard Flammarion, Maksym Andriushchenko

A recent line of work focused on making adversarial training computationally efficient for deep learning models. In particular, Wong et al. (2020) showed that ℓ∞-adversarial training with fast gradient sign method (FGSM) can fail due to a phenomenon called ...

2020

Automatic Feature Learning for Spatio-Spectral Image Classification With Sparse SVM

Devis Tuia

Including spatial information is a key step for successful remote sensing image classification. In particular, when dealing with high spatial resolution, if local variability is strongly reduced by spatial filtering, the classification performance results ...

Ieee-Inst Electrical Electronics Engineers Inc2014

Non-Linear Domain Adaptation with Boosting

Pascal Fua, Carlos Joaquin Becker, Christos Marios Christoudias

A common assumption in machine vision is that the training and test samples are drawn from the same distribution. However, there are many problems when this assumption is grossly violated, as in bio-medical applications where different acquisitions can gen ...

2013

Frequency Domain Controller Design by Linear Programming Guaranteeing Quadratic Stability

Alireza Karimi, Roland Longchamp, Marc Kunze

In a recent work, a frequency method based on linear programming is proposed to design fixed-order linearly parameterized controllers for stable linear multi- model SISO systems. The method is based on the shaping of the open-loop transfer functions in the ...

IEEE2008

Robust Controller Design by Linear Programming with Application to a Double-Axis Positioning System

Alireza Karimi, Roland Longchamp, Marc Kunze

A linear programming approach is proposed to tune fixed-order linearly parameterized controllers for stable LTI plants. The method is based on the shaping of the open-loop transfer function in the Nyquist diagram. A lower bound on the crossover frequency a ...

2007

Melanoma Recognition Using Representative and Discriminative Kernel Classifiers

Barbara Caputo, Tatiana Tommasi

Malignant melanoma is the most deadly for of skin lesion. Early diagnosis is of critical importance to patient survival. Visual recognition algorithms could potentially be of great help for physicians in a computer assisted diagnosis system. Previous work ...

2006

Robust PID Controller Design by Linear Programming

Alireza Karimi, Roland Longchamp, Marc Kunze

2006

A Kernel Classifier for Distributions

Samy Bengio, Alexei Pozdnoukhov

This paper presents a new algorithm for classifying distributions. The algorithm combines the principle of margin maximization and a kernel trick, applied to distributions. Thus, it combines the discriminative power of support vector machines and the well- ...

IDIAP2005

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024