DeepAI AI Chat
Log In Sign Up

A Consistent Regularization Approach for Structured Prediction

05/24/2016
by   Carlo Ciliberto, et al.
MIT
0

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate loss approach and regularization techniques. We prove universal consistency and finite sample bounds characterizing the generalization properties of the proposed methods. Experimental results are provided to demonstrate the practical usefulness of the proposed approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/31/2015

Iterative Regularization for Learning with Convex Loss Functions

We consider the problem of supervised learning with convex loss function...
03/02/2019

Leveraging Low-Rank Relations Between Surrogate Tasks in Structured Prediction

We study the interplay between surrogate methods for structured predicti...
06/26/2018

Manifold Structured Prediction

Structured prediction provides a general framework to deal with supervis...
08/05/2015

Structured Prediction: From Gaussian Perturbations to Linear-Time Principled Algorithms

Margin-based structured prediction commonly uses a maximum loss over all...
06/29/2022

An Embedding Framework for the Design and Analysis of Consistent Polyhedral Surrogates

We formalize and study the natural approach of designing convex surrogat...
09/14/2018

Efficient Structured Surrogate Loss and Regularization in Structured Prediction

In this dissertation, we focus on several important problems in structur...
02/13/2020

A General Framework for Consistent Structured Prediction with Implicit Loss Embeddings

We propose and analyze a novel theoretical and algorithmic framework for...