Matej Balog
Matej Balog
Research Scientist, DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
DeepCoder: Learning to Write Programs
M Balog, AL Gaunt, M Brockschmidt, S Nowozin, D Tarlow
5th International Conference on Learning Representations (ICLR 2017), 2016
3372016
Lost Relatives of the Gumbel Trick
M Balog, N Tripuraneni, Z Ghahramani, A Weller
34th International Conference on Machine Learning (ICML 2017), 2017
202017
Differentially Private Database Release via Kernel Mean Embeddings
M Balog, I Tolstikhin, B Schölkopf
35th International Conference on Machine Learning (ICML 2018), 2018
182018
The Mondrian Kernel
M Balog, B Lakshminarayanan, Z Ghahramani, DM Roy, YW Teh
32nd Conference on Uncertainty in Artificial Intelligence (UAI 2016), 2016
172016
DeepCoder: Learning to write programs. CoRR abs/1611.01989 (2016)
M Balog, AL Gaunt, M Brockschmidt, S Nowozin, D Tarlow
arXiv preprint arXiv:1611.01989, 2016
122016
The Mondrian Process for Machine Learning
M Balog, YW Teh
arXiv preprint arXiv:1507.05181, 2015
52015
Program predictor
AL Gaunt, S Nowozin, MMJ Brockschmidt, DS Tarlow, M Balog
US Patent 10,782,939, 2020
42020
Fast Training of Sparse Graph Neural Networks on Dense Hardware
M Balog, B van Merriënboer, S Moitra, Y Li, D Tarlow
arXiv preprint arXiv:1906.11786, 2019
32019
Neural Program Synthesis with a Differentiable Fixer
M Balog, R Singh, P Maniatis, C Sutton
arXiv preprint arXiv:2006.10924, 2020
12020
Converting to Optimization in Machine Learning: Perturb-and-MAP, Differential Privacy, and Program Synthesis
M Balog
University of Cambridge, 2020
2020
OPTIMIZING SPARSE GRAPH NEURAL NETWORKS FOR DENSE HARDWARE
DS Tarlow, M Balog, B Van Merrienboer, Y Li, S Moitra
US Patent App. 16/883,209, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–11