paper-with-me

홈 › Papers

On Structured Prediction Theory with Calibrated Convex Surrogate Losses

2017-03-07 · NeurIPS 2017 12 · Anton Osokin, Francis Bach, Simon Lacoste-Julien

We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via stochastic gradient descent and we prove tight bounds on the so-called "calibration function" relating the excess surrogate risk to the actual risk. In contrast to prior related work, we carefully monitor the effect of the exponential number of classes in the learning guarantees as well as on the optimization complexity. As an interesting consequence, we formalize the intuition that some task losses make learning harder than others, and that the classical 0-1 loss is ill-suited for general structured prediction.

📄 PDF Abstract BibTeX arXiv:1703.02403

Code (1)

aosokin/consistentSurrogates_derivations 공식 구현

Tasks

PredictionStructured Prediction

Similar Papers 제목 키워드 기반

A General Theory for Structured Prediction with Smooth Convex Surrogates

2019-02-05 · Alex Nowak-Vila, Francis Bach, Alessandro Rudi

In this work we provide a theoretical framework for structured prediction that generalizes the existing theory of surrogate methods for binary and multiclass classification based on estimating conditional probabilities w…

General ClassificationGraph MatchingregressionStructured Prediction

Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses

2013-12-01 · NeurIPS 2013 12 · Harish G. Ramaswamy, Shivani Agarwal, Ambuj Tewari

The design of convex, calibrated surrogate losses, whose minimization entails consistency with respect to a desired target loss, is an important concept to have emerged in the theory of machine learning in recent years. …

Convex Calibration Dimension for Multiclass Loss Matrices

2014-08-12 · Harish G. Ramaswamy, Shivani Agarwal

We study consistency properties of surrogate loss functions for general multiclass learning problems, defined by a general multiclass loss matrix. We extend the notion of classification calibration, which has been studie…

General Classification

Structured Prediction with Projection Oracles

2019-10-24 · NeurIPS 2019 12 · Mathieu Blondel

We propose in this paper a general framework for deriving loss functions for structured prediction. In our framework, the user chooses a convex set including the output space and provides an oracle for projecting onto th…

PredictionStructured Prediction

Calibrated Surrogate Losses for Adversarially Robust Classification

2020-05-28 · Han Bao, Clayton Scott, Masashi Sugiyama

Adversarially robust classification seeks a classifier that is insensitive to adversarial perturbations of test patterns. This problem is often formulated via a minimax objective, where the target loss is the worst-case …

ClassificationGeneral ClassificationRobust classification