• Publications
  • Influence
Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class
TLDR
A fundamental question in multiclass classification concerns understanding the consistency properties of surrogate risk minimization algorithms, which minimize a (often convex) surrogate to the multiclass 0-1 loss. Expand
Convex Calibrated Surrogates for the Multi-Label F-Measure
TLDR
We show that the F-measure for an $s$-label problem, when viewed as a $2^s \times 2^s$ loss matrix, has rank at most $s^2+1$, and apply a result of Ramaswamy et al. (2014) to design a family of convex calibrated surrogates. Expand
Foreshadowing the Benefits of Incidental Supervision
TLDR
We propose a unified PAC-Bayesian Informativeness measure (PABI), characterizing the reduction in uncertainty that incidental supervision signals provide. Expand
Ordinal Embedding with a Latent Factor Model
Constructing low-dimensional embeddings based on ordinal measurements has been a subject of significant recent interest, motivated in part by machine learning applications using human input in aExpand