Martin Takác
Artificial Intelligence · 2011–2021
A researcher in the Science corpus: 29 papers; trusts 1,018 researchers and is trusted by 982 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 507 citations into it; #933 of 36,961 by trust here, #1,149 by citations
- Optimization & Training — 374 citations into it; #125 of 2,605 by trust here, #147 by citations
- Computational Mechanics — 277 citations into it; #41 of 10,021 by trust here, #49 by citations
- Numerical Analysis — 132 citations into it; #1,340 of 3,703 by trust here, #994 by citations
- Statistics and Probability — 116 citations into it; #1,277 of 13,188 by trust here, #1,876 by citations
- Computer Vision and Pattern Recognition — 113 citations into it; #8,373 of 21,973 by trust here, #5,300 by citations
- Computational Theory and Mathematics — 111 citations into it; #270 of 12,489 by trust here, #327 by citations
- Management Science and Operations Research — 69 citations into it; #2,445 of 12,201 by trust here, #1,023 by citations
Whom Martin Takác trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Peter Richtárik
- Shai Shalev-Shwartz
- Yurii E. Nesterov
- Tong Zhang
- Olivier Fercoq
- Tianbao Yang
- Alex Krizhevsky
- Geoffrey E. Hinton
- L. Eon Bottou
- Yoshua Bengio
Who trusts Martin Takác overall
- Peter Richtárik
- Jakub Konecný
- Nicolas Loizou
- Chenxin Ma
- Zheng Qu
- Virginia Smith
- Samuel Horváth
- Martin Jaggi
- Dominik Csiba
- Olivier Fercoq
Papers from Martin Takác's perspective
Ordered by how strongly the researchers Martin Takác trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Communication-Efficient Distributed Dual Coordinate Ascent (2014) — 363 citations
- Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function (2011) — 819 citations
- Parallel coordinate descent methods for big data optimization (2012) — 500 citations
- Mini-Batch Primal and Dual Methods for SVMs (2013) — 197 citations
- Improving Text-to-Image Synthesis Using Contrastive Learning (2021) — 93 citations
- Distributed Coordinate Descent Method for Learning with Big Data (2013) — 262 citations
- Adding vs. Averaging in Distributed Primal-Dual Optimization (2015) — 178 citations
- Distributed Mini-Batch SDCA (2015) — 50 citations
- Distributed optimization with arbitrary local solvers (2015) — 206 citations
- SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient (2017) — 717 citations
- Distributed Block Coordinate Descent for Minimizing Partially Separable Functions (2014) — 64 citations
- CoCoA: A General Framework for Communication-Efficient Distributed Optimization (2016) — 285 citations
- Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting (2015) — 279 citations
- Fast distributed coordinate descent for non-strongly convex losses (2014) — 59 citations
- On optimal probabilities in stochastic coordinate descent methods (2013) — 132 citations
- SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization (2015) — 105 citations
- Primal-Dual Rates and Certificates (2016) — 60 citations
- Stochastic Recursive Gradient Algorithm for Nonconvex Optimization (2017) — 100 citations
- On the Acceleration of L-BFGS with Second-Order Information and Stochastic Batches (2018) — 7 citations
- SGD and Hogwild! Convergence Without the Bounded Gradients Assumption (2018) — 251 citations