249 citations · 452 across the 8 of their papers we have counts for
5 papers · 1 filter
Tight Error Bounds for Structured Prediction
Amir Globerson, Tim Roughgarden, David Sontag +1
Structured prediction tasks in machine learning involve the simultaneous prediction of multiple labels. This is typically done by maximizing a score function on the space of labels…
Discriminative Learning via Semidefinite Probabilistic Models
Koby Crammer, Amir Globerson
Discriminative linear models are a popular tool in machine learning. These can be generally divided into two types: The first is linear classifiers, such as support vector machines…
Convergent Propagation Algorithms via Oriented Trees
Amir Globerson, Tommi S. Jaakkola
Inference problems in graphical models are often approximated by casting them as constrained optimization problems. Message passing algorithms, such as belief propagation, have pre…
Learning the Experts for Online Sequence Prediction
Elad Eban, Aharon Birnbaum, Shai Shalev-Shwartz +1
Online sequence prediction is the problem of predicting the next element of a sequence given previous elements. This problem has been extensively studied in the context of individu…
What Cannot be Learned with Bethe Approximations
Uri Heinemann, Amir Globerson
We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its Be…