Randomized Optimum Models for Structured Prediction

By Daniel Tarlow, Ryan P. Adams, Richard S. Zemel. 2012

53 citations recorded by the source corpus.

Subfields: Optimization & Training, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

In Information Extraction

Citations in the corpus

A* Sampling (2014, methodology): “The problem of drawing samples from a discrete distribution can be converted into a discrete optimization problem [1, 2, 3, 4].”
Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement (2019, methodology): “The idea of sampling by solving optimization problems has been used for various purposes (Papandreou & Yuille, 2011; Hazan & Jaakkola, 2012; Tarlow et al., 2012; Ermon et al., 2013; Maddison et al., 2014; Chen & Ghahramani, 2016; Balog et al., 2017), but to our knowledge this idea has not been used…”
On the Partition Function and Random Maximum A-Posteriori Perturbations (2012, background): “For a more general class of probabilistic models that exploit eﬃcient optimization we refer to (Tarlow et al., 2012).”
Direct Optimization through arg max for Discrete Variational Auto-Encoder (2019, methodology): “The Gumbel-Softmax approach is motivated by the connection of the Gumbel-Max perturbation model and the Gibbs distribution [27, 34, 7, 18].”
On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations (2013, methodology): “The Gibbs distribution and its partition function can be realized from the statistics of random MAP perturbations with the Gumbel distribution (see Theorem 1), [12, 17, 21, 5].”
Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions (2013, methodology): “[23] describes the Bayesian perspectives, while [17, 8] describe their relations to the Gibbs distribution and moment matching.”