Approximate inference for the loss-calibrated Bayesian

By Simon Lacoste-Julien, Ferenc Huszár, Zoubin Ghahramani. 2011

79 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

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

In Probabilistic & Bayesian Methods

Citations in the corpus

GAIT: A Geometric Approach to Information Theory (2019, methodology): “…bottleneck for representation learning (Tishby and Zaslavsky, 2015), similarity-sensitive cross entropy objectives in the spirit of loss-calibrated decision theory (Lacoste-Julien et al., 2011), or the use of entropic regularization of policies in reinforcement learning (Fox et al., 2016).”
PAC-Bayesian Theory Meets Bayesian Inference (2016, neutral): “See also Grünwald and Langford [17], Lacoste-Julien et al. [26], Meir and Zhang [35], Ng and Jordan [36], Rousseau [40] for other studies drawing links between frequentist statistics and Bayesian inference, but outside the PAC-Bayesian framework.”
A note on the evaluation of generative models (2015, methodology): “These issues can be addressed by better image models (e.g., Kingma et al., 2014), better optimization and inference procedures, or a more Bayesian treatment of the parameters (e.g., Lacoste-Julien et al., 2011; Welling & Teh, 2011).”
DISCO Nets : DISsimilarity COefficients Networks (2016, background): “[12], we argue that the learning objective should be tailored to the evaluation loss in order to obtain the best performance with respect to this loss.”
POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning (2020, methodology): “More broadly, “end-to-end” optimization methods directly incorporate a downstream decision-making task during model training, and are growing in popularity across machine learning, from graphical models (Lacoste–Julien et al., 2011) to submodular optimization (Wilder et al.”
Inconsistency of Bayesian Inference for Misspecified Linear Models, and a Proposal for Repairing It (2014, background): “lso Grun wald (1999)) under the name of entropication (however, Grun wald’s papers wrongly suggest that, by introducing the scale parameter , it would be sucient to only consider = 1); see also (Lacoste-Julien et al., 2011, Quadrianto and Ghahramani, 2015). Now both ‘pure’ subjective Bayesians and ‘”
Minimum-Risk Training of Approximate CRF-Based NLP Systems (2012, background): “Lacoste-Julien et al. (2011) also consider the effects of approximate inference on loss.”
Advances in Variational Inference (2017, background): “Despite progress in modeling and inference, few authors address theoretical aspects of VI [95], [133], [213].”
AUTO-ENCODING VARIATIONAL BAYES (2020, unknown): “An alternative approach to decision-making is the elegant framework of loss-calibrated inference [45, 46], which further adapts the ELBO to take into account the loss function L.”