Complementary Sum Sampling for Likelihood Approximation in Large Scale Classification

By Aleksandar Botev, Bowen Zheng, David Barber. 2017

28 citations recorded by the source corpus.

Subfields: Optimization & Training, Statistical Learning Theory

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

1. Francisco J. R. Ruiz
2. Rahul G. Krishnan
3. Matthias Bauer
4. Dawen Liang
5. Andriy Mnih
6. Michalis K. Titsias
7. Tony Jebara
8. David M. Blei

In Statistical Learning Theory

1. Adji Bousso Dieng
2. Matthias Bauer
3. Andriy Mnih
4. Michalis K. Titsias
5. Tony Jebara
6. David M. Blei
7. Matthew D. Hoffman
8. Barnab'as P'oczos

Citations in the corpus

• Variational Autoencoders for Collaborative Filtering (2018, methodology): “If this becomes a bottleneck when working with larger item sets, one can easily apply the simple and effective method proposed by Botev et al. [6] to approximate the normalization factor for π ( z u ) .”
• Resampled Priors for Variational Autoencoders (2018, methodology): “Unless otherwise stated, we used warm-up (KL-annealing) for the first 10(5) iterations [2].”
• Augment and Reduce: Stochastic Inference for Large Categorical Distributions (2018, background): “, 2014), those that rely on sampling (Bengio & Sénécal, 2003; Mikolov et al., 2013; Devlin et al., 2014; Ji et al., 2016; Botev et al., 2017), those that use approximations and distributed computing (Grave et al.”