Aryan Mokhtari
Artificial Intelligence · 2014–2022
A researcher in the Science corpus: 21 papers; trusts 918 researchers and is trusted by 112 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 451 citations into it; #4,291 of 36,961 by trust here, #5,035 by citations
- Optimization & Training — 284 citations into it; #620 of 2,605 by trust here, #864 by citations
- Computer Networks and Communications — 184 citations into it; #1,000 of 9,996 by trust here, #1,295 by citations
- Computational Mechanics — 167 citations into it; #476 of 10,021 by trust here, #849 by citations
- Federated & Distributed Learning — 101 citations into it; #43 of 319 by trust here, #79 by citations
- Computer Vision and Pattern Recognition — 82 citations into it
- Numerical Analysis — 76 citations into it; #332 of 3,703 by trust here, #556 by citations
- Computational Theory and Mathematics — 75 citations into it
Whom Aryan Mokhtari trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- L. Eon Bottou
- Yurii E. Nesterov
- Tong Zhang
- Shai Shalev-Shwartz
- Angelia Nedić
- Alex Krizhevsky
- Aaron Defazio
- Francis R. Bach
- Geoffrey E. Hinton
- Yoshua Bengio
Who trusts Aryan Mokhtari overall
- Amirhossein Reisizadeh
- Waïss Azizian
- Mark Eisen
- Angelia Nedić
- Can Bülent Karakus
- Alireza Fallah
- Albert S. Berahas
- S. Meng
- Zachary B. Charles
- Hanlin Tang
Papers from Aryan Mokhtari's perspective
Ordered by how strongly the researchers Aryan Mokhtari 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
- Learning Multiple Layers of Features from Tiny Images
- Attention is All you Need (Neural Information Processing Systems)
- 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
- Personalized Federated Learning: A Meta-Learning Approach (2020) — 720 citations
- A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach (2019) — 380 citations
- Exploiting Shared Representations for Personalized Federated Learning (2021) — 1,173 citations
- On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms (2019) — 268 citations
- FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization (2019) — 974 citations
- DSA: Decentralized Double Stochastic Averaging Gradient Algorithm (2015) — 171 citations
- Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy (2016) — 33 citations
- Robust and Communication-Efficient Collaborative Learning (2019) — 98 citations
- A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem (2022) — 40 citations
- Federated Learning with Compression: Unified Analysis and Sharp Guarantees (2020) — 337 citations
- Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach (2020) — 1,273 citations
- Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication (2018) — 60 citations
- Quantized Decentralized Consensus Optimization (2018) — 30 citations
- Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy (2018) — 21 citations
- An Exact Quantized Decentralized Gradient Descent Algorithm (2018) — 139 citations
- IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate (2017) — 79 citations
- Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method (2017) — 16 citations
- Optimization in Dynamic Environments : Improved Regret Rates for Strongly Convex Problems (2016)
- Decentralized double stochastic averaging gradient (2015) — 11 citations
- DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers (2015) — 122 citations