Lukas Balles
Optimization & Training · 2016–2019
A researcher in the Science corpus: 7 papers; trusts 318 researchers and is trusted by 35 researchers here, as inferred from the citation graph.
Subfields
- Optimization & Training — 110 citations into it; #581 of 2,601 by trust here, #1,009 by citations
- Artificial Intelligence — 98 citations into it; #8,539 of 35,345 by trust here, #13,544 by citations
- Computer Vision and Pattern Recognition — 84 citations into it; #10,892 of 21,575 by trust here, #9,722 by citations
- Model Architectures — 22 citations into it
- Computational Mechanics — 21 citations into it
- Management Science and Operations Research — 16 citations into it
- Evaluation & Benchmarks — 15 citations into it; #2,462 of 3,147 by trust here, #3,037 by citations
- Statistical and Nonlinear Physics — 12 citations into it
Whom Lukas Balles trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Diederik P. Kingma
- Yann LeCun
- Geoffrey E. Hinton
- Matthew D. Zeiler
- Yoshua Bengio
- Yurii E. Nesterov
- L. Eon Bottou
- James Martens
- Jimmy Ba
Who trusts Lukas Balles overall
- Felix Dangel
- Dami Choi
- Philipp Hennig
- Frederik Kunstner
- Jianyu Wang
- Mohamed Reyad
- Jiawei Zhao
- Christopher J. Shallue
- Sai Praneeth Karimireddy
- Samuel L. Smith
Papers from Lukas Balles's perspective
Ordered by how strongly the researchers Lukas Balles 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
- Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation (2018) — 640 citations
- Coupling Adaptive Batch Sizes with Learning Rates (2016) — 124 citations
- DeepOBS: A Deep Learning Optimizer Benchmark Suite (2019) — 79 citations
- Limitations of the Empirical Fisher Approximation (2019) — 290 citations
- Follow the Signs for Robust Stochastic Optimization (2017) — 5 citations
- Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients (2017) — 229 citations
- Early Stopping without a Validation Set (2017) — 113 citations