Guanghui Lan
Optimization & Training · 2008–2020
A researcher in the Science corpus: 21 papers; trusts 216 researchers and is trusted by 2,003 researchers here, as inferred from the citation graph.
Subfields
- Optimization & Training — 179 citations into it; #52 of 2,605 by trust here, #118 by citations
- Artificial Intelligence — 167 citations into it; #605 of 36,961 by trust here, #1,696 by citations
- Computational Mechanics — 154 citations into it; #29 of 10,021 by trust here, #107 by citations
- Numerical Analysis — 135 citations into it; #182 of 3,703 by trust here, #192 by citations
- Computational Theory and Mathematics — 131 citations into it; #685 of 12,489 by trust here, #3,295 by citations
- Mathematical Optimization — 85 citations into it; #48 of 422 by trust here, #80 by citations
- Management Science and Operations Research — 78 citations into it; #41 of 12,201 by trust here, #119 by citations
- Statistics and Probability — 67 citations into it; #5,000 of 13,188 by trust here, #2,170 by citations
Whom Guanghui Lan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yurii E. Nesterov
- Alexander Shapiro
- Anatoli B. Juditsky
- Arkadi Nemirovski
- Boris Polyak
- Saeed Ghadimi
- Dimitri P. Bertsekas
- Alfred Auslender
- S. Burer
- Alexandre d'Aspremont
Who trusts Guanghui Lan overall
- Saeed Ghadimi
- John C. Duchi
- Julien Mairal
- Francis R. Bach
- Simon Lacoste-Julien
- Zeyuan Allen-Zhu
- Michael G. Rabbat
- Sashank J. Reddi
- Hanlin Tang
- Xiao Wang
Papers from Guanghui Lan's perspective
Ordered by how strongly the researchers Guanghui Lan 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
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- Regression Shrinkage and Selection via the Lasso
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming (2013) — 1,919 citations
- An optimal method for stochastic composite optimization (2011) — 597 citations
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework (2012) — 398 citations
- Robust Stochastic Approximation Approach to Stochastic Programming (2008) — 932 citations
- Accelerated gradient methods for nonconvex nonlinear and stochastic programming (2013) — 627 citations
- Optimal Primal-Dual Methods for a Class of Saddle Point Problems (2013) — 280 citations
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms (2013) — 230 citations
- Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization (2013) — 565 citations
- Validation analysis of mirror descent stochastic approximation method (2012) — 156 citations
- The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle (2013) — 144 citations
- Communication-efficient algorithms for decentralized and stochastic optimization (2017) — 239 citations
- Theoretical properties of the global optimizer of two layer neural network (2017) — 34 citations
- Accelerated schemes for a class of variational inequalities (2014) — 138 citations
- Algorithms for stochastic optimization with expectation constraints (2016) — 52 citations
- First-order and Stochastic Optimization Methods for Machine Learning (2020) — 452 citations
- Asynchronous Decentralized Accelerated Stochastic Gradient Descent (2018) — 15 citations
- Randomized First-Order Methods for Saddle Point Optimization (2014) — 45 citations
- Stochastic Approximation approach to Stochastic Programming (2013) — 1,732 citations
- Primal-dual first-order methods with $${\mathcal {O}(1/\epsilon)}$$ iteration-complexity for cone programming (2011) — 83 citations
- Primal-dual first-order methods with O (1/e) iteration-complexity for cone programming. (2011) — 178 citations