Philipp Hennig
Artificial Intelligence · 2011–2021
A researcher in the Science corpus: 25 papers; trusts 1,244 researchers and is trusted by 340 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 446 citations into it; #1,798 of 36,961 by trust here, #3,738 by citations
- Optimization & Training — 236 citations into it; #370 of 2,605 by trust here, #519 by citations
- Computer Vision and Pattern Recognition — 129 citations into it; #12,499 of 21,973 by trust here, #13,855 by citations
- Probabilistic & Bayesian Methods — 112 citations into it; #258 of 1,526 by trust here, #431 by citations
- Computational Theory and Mathematics — 97 citations into it; #523 of 12,489 by trust here, #1,107 by citations
- Statistics and Probability — 96 citations into it; #11,093 of 13,188 by trust here, #7,717 by citations
- Management Science and Operations Research — 81 citations into it; #520 of 12,201 by trust here, #911 by citations
- Numerical Analysis — 66 citations into it; #430 of 3,703 by trust here, #668 by citations
Whom Philipp Hennig trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- James Martens
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Yann LeCun
- Yoshua Bengio
- Radford M. Neal
- David F. Shanno
- Donald Goldfarb
- C. G. Broyden
Who trusts Philipp Hennig overall
- Aaron Klein
- Zoubin Ghahramani
- José Miguel Hernández-Lobato
- Bobak Shahriari
- Ziyun Wang
- Chris J. Oates
- Stefan Falkner
- Jon Cockayne
- Marc-André Zöller
- Frank Hutter
Papers from Philipp Hennig's perspective
Ordered by how strongly the researchers Philipp Hennig trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Entropy Search for Information-Efficient Global Optimization (2011) — 745 citations
- Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets (2016) — 620 citations
- Probabilistic Line Searches for Stochastic Optimization (2015) — 133 citations
- Batch Bayesian Optimization via Local Penalization (2015) — 413 citations
- Coupling Adaptive Batch Sizes with Learning Rates (2016) — 124 citations
- Active Learning of Linear Embeddings for Gaussian Processes (2013) — 104 citations
- Approximate Gaussian Integration using Expectation Propagation (2011) — 40 citations
- DeepOBS: A Deep Learning Optimizer Benchmark Suite (2019) — 79 citations
- Fast Probabilistic Optimization from Noisy Gradients (2013) — 35 citations
- Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks (2020) — 365 citations
- Probabilistic numerics and uncertainty in computations (2015) — 331 citations
- Follow the Signs for Robust Stochastic Optimization (2017) — 5 citations
- Fast Bayesian hyperparameter optimization on large datasets (2017) — 67 citations
- Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature (2014) — 121 citations
- Quasi-Newton Methods: A New Direction (2012) — 110 citations
- Probabilistic ODE Solvers with Runge-Kutta Means (2014) — 127 citations
- Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences (2018) — 431 citations
- Laplace Redux - Effortless Bayesian Deep Learning (2021) — 467 citations
- Limitations of the Empirical Fisher Approximation (2019) — 290 citations
- BackPACK: Packing more into backprop (2019) — 117 citations