Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss
نویسندگان
چکیده
We consider latent structural versions of probit loss and ramp loss. We show that these surrogate loss functions are consistent in the strong sense that for any feature map (finite or infinite dimensional) they yield predictors approaching the infimum task loss achievable by any linear predictor over the given features. We also give finite sample generalization bounds (convergence rates) for these loss functions. These bounds suggest that probit loss converges more rapidly. However, ramp loss is more easily optimized on a given sample.
منابع مشابه
The Analysis of Bayesian Probit Regression of Binary and Polychotomous Response Data
The goal of this study is to introduce a statistical method regarding the analysis of specific latent data for regression analysis of the discrete data and to build a relation between a probit regression model (related to the discrete response) and normal linear regression model (related to the latent data of continuous response). This method provides precise inferences on binary and multinomia...
متن کاملRisk Minimization in Structured Prediction using Orbit Loss
We introduce a new surrogate loss function called orbit loss in the structured prediction framework, which has good theoretical and practical advantages. While the orbit loss is not convex, it has a simple analytical gradient and a simple perceptron-like learning rule. We analyze the new loss theoretically and state a PAC-Bayesian generalization bound. We also prove that the new loss is consist...
متن کاملComputational Complexity of Linear Large Margin Classification With Ramp Loss
Minimizing the binary classification error with a linear model leads to an NP-hard problem. In practice, surrogate loss functions are used, in particular loss functions leading to large margin classification such as the hinge loss and the ramp loss. The intuitive large margin concept is theoretically supported by generalization bounds linking the expected classification error to the empirical m...
متن کاملA Multivariate Probit Latent Variable Model for Analyzing Dichotomous Responses
We propose a multivariate probit model that is defined by a confirmatory factor analysis model with covariates for analyzing dichotomous data in medical research. Our proposal is a generalization of several useful multivariate probit models, and provides a flexible framework for practical applications. We implement a Monte Carlo EM algorithm for maximum likelihood estimation of the model, and d...
متن کاملProbit-Based Traffic Assignment: A Comparative Study between Link-Based Simulation Algorithm and Path-Based Assignment and Generalization to Random-Coefficient Approach
Probabilistic approach of traffic assignment has been primarily developed to provide a more realistic and flexible theoretical framework to represent traveler’s route choice behavior in a transportation network. The problem of path overlapping in network modelling has been one of the main issues to be tackled. Due to its flexible covariance structure, probit model can adequately address the pro...
متن کامل