Sham M. Kakade
Artificial Intelligence · 2001–2024
A researcher in the Science corpus: 81 papers; trusts 2,010 researchers and is trusted by 9,128 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,261 citations into it; #118 of 36,961 by trust here, #404 by citations
- Reinforcement Learning — 508 citations into it; #16 of 2,250 by trust here, #103 by citations
- Management Science and Operations Research — 347 citations into it; #25 of 12,201 by trust here, #49 by citations
- Optimization & Training — 346 citations into it; #218 of 2,605 by trust here, #314 by citations
- Computer Vision and Pattern Recognition — 247 citations into it; #1,774 of 21,973 by trust here, #2,134 by citations
- Statistics and Probability — 215 citations into it; #1,296 of 13,188 by trust here, #820 by citations
- Computational Mechanics — 210 citations into it; #610 of 10,021 by trust here, #269 by citations
- Computational Theory and Mathematics — 205 citations into it; #571 of 12,489 by trust here, #186 by citations
Whom Sham M. Kakade trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Francis R. Bach
- Richard S. Sutton
- Geoffrey E. Hinton
- Yurii E. Nesterov
- Tong Zhang
- Alex Krizhevsky
- Diederik P. Kingma
- Yoshua Bengio
- Shai Shalev-Shwartz
- Kaiming He
Who trusts Sham M. Kakade overall
- Sergey Levine
- Jan Peters
- Csaba Szepesvari
- Lihong Li
- Alekh Agarwal
- Aravind Rajeswaran
- Pieter Abbeel
- Wen Sun
- R´emi Munos
- J. Bagnell
Papers from Sham M. Kakade's perspective
Ordered by how strongly the researchers Sham M. Kakade 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
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- 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
- A Natural Policy Gradient (2001) — 1,429 citations
- Approximately Optimal Approximate Reinforcement Learning (2002) — 1,346 citations
- Towards Generalization and Simplicity in Continuous Control (2017) — 294 citations
- On the sample complexity of reinforcement learning. (2003) — 755 citations
- Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting (2009) — 1,787 citations
- Tensor decompositions for learning latent variable models (2012) — 1,214 citations
- Multi-Label Prediction via Compressed Sensing (2009) — 443 citations
- Cover trees for nearest neighbor (2006) — 994 citations
- Learning from Logged Implicit Exploration Data (2010) — 267 citations
- How to Escape Saddle Points Efficiently (2017) — 945 citations
- Meta-Learning with Implicit Gradients (2019) — 1,013 citations
- Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines (2018) — 173 citations
- On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization (2008) — 412 citations
- Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control (2018) — 268 citations
- Stochastic Linear Optimization under Bandit Feedback (2008) — 969 citations
- A Method of Moments for Mixture Models and Hidden Markov Models (2012) — 349 citations
- Multi-view clustering via canonical correlation analysis (2009) — 845 citations
- Optimizing Average Reward Using Discounted Rewards (2001) — 46 citations
- A Spectral Algorithm for Latent Dirichlet Allocation (2012) — 304 citations
- Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes (2019) — 345 citations