Structured prediction with stronger consistency guarantees
We present an extensive study of surrogate losses for structured prediction supported by* $
H $-consistency bounds*. These are recently introduced guarantees that are more relevant …
H $-consistency bounds*. These are recently introduced guarantees that are more relevant …
A universal growth rate for learning with smooth surrogate losses
This paper presents a comprehensive analysis of the growth rate of $ H $-consistency
bounds (and excess error bounds) for various surrogate losses used in classification. We …
bounds (and excess error bounds) for various surrogate losses used in classification. We …
Moment distributionally robust tree structured prediction
Structured prediction of tree-shaped objects is heavily studied under the name of syntactic
dependency parsing. Current practice based on maximum likelihood or margin is either …
dependency parsing. Current practice based on maximum likelihood or margin is either …
An embedding framework for the design and analysis of consistent polyhedral surrogates
We formalize and study the natural approach of designing convex surrogate loss functions
via embeddings, for discrete problems such as classification, ranking, or structured …
via embeddings, for discrete problems such as classification, ranking, or structured …
On the inconsistency of separable losses for structured prediction
C Corro - arxiv preprint arxiv:2301.10810, 2023 - arxiv.org
In this paper, we prove that separable negative log-likelihood losses for structured prediction
are not necessarily Bayes consistent, or, in other words, minimizing these losses may not …
are not necessarily Bayes consistent, or, in other words, minimizing these losses may not …
Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
This paper studies online structured prediction with full-information feedback. For online
multiclass classification, van der Hoeven (2020) has obtained surrogate regret bounds …
multiclass classification, van der Hoeven (2020) has obtained surrogate regret bounds …
Teacher guided training: An efficient framework for knowledge transfer
The remarkable performance gains realized by large pretrained models, eg, GPT-3, hinge
on the massive amounts of data they are exposed to during training. Analogously, distilling …
on the massive amounts of data they are exposed to during training. Analogously, distilling …