🧑‍🔬 Andriy Mnih

🏛️ Affiliations

🏢Google DeepMindLondon · United Kingdom2013–2026 · 10 paperscurrent🏢GoogleLondon · United Kingdom2026 · 1 papercurrent🏢GoogleMountain View · United States2015–2021 · 13 papers🎓University of TorontoToronto · Canada2003–2010 · 9 papers🔬Gatsby Computational Neuroscience UnitLondon · United Kingdom2011–2012 · 3 papers🎓University College LondonLondon · United Kingdom2011–2012 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables (2016 · 1,629 citations)
   Gradient-based training of models with random choices works well when each random node can be rewritten as a differentiable function of its parameters plus fixed noise.
2. A Fast and Simple Algorithm for Training Neural Probabilistic Language Models (2012 · 408 citations)
   Neural probabilistic language models (NPLMs) tend to beat n-gram models, but they are slow to train. The softmax normalization forces every gradient step to score the entire vocabulary. Mnih and Teh adapt noise-contrastive estimation (NCE), introduced by Gutmann and Hyvärinen for unnormalized densities, to discrete…

All works

10 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Probabilistic Matrix Factorization ↗neural information processing systems · no summary yetAndriy Mnih, Ruslan Salakhutdinov2007 · 3,483 citations
2. Restricted Boltzmann machines for collaborative filtering ↗International Conference on Machine Learning · no summary yetRuslan Salakhutdinov, Andriy Mnih, Geoffrey E. Hinton2007 · 1,865 citations
3. The Concrete Distribution: A Continuous Relaxation of Discrete Random VariablesarXiv:1611.00712Chris J. Maddison, Andriy Mnih, Yee Whye Teh2016 · 1,629 citations
4. Bayesian probabilistic matrix factorization using Markov chain Monte Carlo ↗International Conference on Machine Learning · no summary yetRuslan Salakhutdinov, Andriy Mnih2008 · 1,437 citations
5. Learning word embeddings efficiently with noise-contrastive estimation ↗neural information processing systems · no summary yetAndriy Mnih, Koray Kavukcuoglu2013 · 505 citations
6. A Fast and Simple Algorithm for Training Neural Probabilistic Language ModelsarXiv:1206.6426 · In Proceedings of the 29th International Conference on Machine Learning, pages 1751-1758, 2012Andriy Mnih, Yee Whye Teh2012 · 408 citations
7. Attentive Neural Processes ↗arXiv (Cornell University) · no summary yetHyunjik Kim et al.2019 · 33 citations
8. Wormholes Improve Contrastive Divergence ↗no summary yetMax Welling, Andriy Mnih, Geoffrey E. Hinton2003 · 12 citations
9. Learning word embeddings efficiently with noise-contrastive ↗no summary yetAndriy Mnih, Koray Kavukcuoglu2014
10. Bayesian probabilistic matrix factorization using MCMC ↗no summary yetRuslan Salakhutdinov, Andriy Mnih2008

🤝 Co-authors here

2 co-authors with a page, the most papers together first.

• Yee Whye Teh ×2
• Chris J. Maddison

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• International Conference on Machine Learning ×2
• neural information processing systems ×2

🔗 Cited by

Papers of our library cite their works 590 times (of the 149,439 papers whose bibliographies we read); 48 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/andriy-mnih/