Sotabase

Career

· Senior Vice President, D. E. Shaw & Co2020–2021
· Associate Professor, Carnegie Mellon University2018–
· Assistant Professor, Carnegie Mellon University2012–2018
· Postdoctoral Researcher, Carnegie Mellon University2010–2012
· Postdoctoral Researcher, University of Alberta2007–2010
· Assistant Professor, Eötvös Loránd University2005–2007
· Lecturer, Eötvös Loránd University2004–2005
· PhD in Computer Science, Eötvös Loránd University2001–2007
· M.Sc., Applied Mathematics, Eötvös Loránd University1996–2001

Publications (251)

Deep Sets
2017
2,756
cited
Gradient Descent Provably Optimizes Over-parameterized Neural Networks
International Conference on Learning Representations · 2018
1,340
cited
MMD GAN: Towards Deeper Understanding of Moment Matching Network
Neural Information Processing Systems · 2017
764
cited
Neural Architecture Search with Bayesian Optimisation and Optimal Transport
Neural Information Processing Systems · 2018
646
cited
Stochastic Variance Reduction for Nonconvex Optimization
International Conference on Machine Learning · 2016
634
cited
Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
AAAI Conference on Artificial Intelligence · 2018
500
cited
Characterizing and Avoiding Negative Transfer
Computer Vision and Pattern Recognition · 2018
468
cited
High Dimensional Bayesian Optimisation and Bandits via Additive Models
International Conference on Machine Learning · 2015
397
cited
Competence-based Curriculum Learning for Neural Machine Translation
North American Chapter of the Association for Computational Linguistics · 2019
392
cited
One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models
IEEE International Conference on Computer Vision · 2017
354
cited
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
Neural Information Processing Systems · 2019
300
cited
Equivariance Through Parameter-Sharing
International Conference on Machine Learning · 2017
279
cited
Parallelised Bayesian Optimisation via Thompson Sampling
International Conference on Artificial Intelligence and Statistics · 2018
267
cited
Gradient Descent Can Take Exponential Time to Escape Saddle Points
Neural Information Processing Systems · 2017
253
cited
Multi-fidelity Bayesian Optimisation with Continuous Approximations
International Conference on Machine Learning · 2017
243
cited
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
International Conference on Machine Learning · 2017
241
cited
Point Cloud GAN
DGS@ICLR · 2018
226
cited
Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization
Neural Information Processing Systems · 2016
203
cited
On the Decreasing Power of Kernel and Distance Based Nonparametric Hypothesis Tests in High Dimensions
AAAI Conference on Artificial Intelligence · 2014
202
cited
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants
Neural Information Processing Systems · 2015
199
cited
Sotabase
Barnabas Poczos | Researcher Profile | Sotabase | Sotabase