Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Opponent interactions between serotonin and dopamine
Countries citing papers authored by Sham M. Kakade
Since
Specialization
Citations
This map shows the geographic impact of Sham M. Kakade's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Sham M. Kakade with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Sham M. Kakade more than expected).
This network shows the impact of papers produced by Sham M. Kakade. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Sham M. Kakade. The network helps show where Sham M. Kakade may publish in the future.
Co-authorship network of co-authors of Sham M. Kakade
This figure shows the co-authorship network connecting the top 25 collaborators of Sham M. Kakade.
A scholar is included among the top collaborators of Sham M. Kakade based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Sham M. Kakade. Sham M. Kakade is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Zou, Difan, Jingfeng Wu, Vladimir Braverman, et al.. (2021). The Benefits of Implicit Regularization from SGD in Least Squares Problems. arXiv (Cornell University). 34.1 indexed citations
2.
Wang, Ruosong, et al.. (2021). An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap. arXiv (Cornell University). 34.1 indexed citations
3.
Agarwal, Alekh, Sham M. Kakade, Akshay Krishnamurthy, & Wen Sun. (2020). FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs. arXiv (Cornell University). 33. 20095–20107.1 indexed citations
4.
Ge, Rong, Sham M. Kakade, Rahul Kidambi, & Praneeth Netrapalli. (2019). The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure.. arXiv (Cornell University).6 indexed citations
5.
Jin, Chi, Praneeth Netrapalli, Rong Ge, Sham M. Kakade, & Michael I. Jordan. (2019). Stochastic Gradient Descent Escapes Saddle Points Efficiently.. arXiv (Cornell University).19 indexed citations
6.
Bagnell, J. Andrew, Sham M. Kakade, Andrew Y. Ng, & Jeff Schneider. (2018). Policy Search by Dynamic Programming. ScholarlyCommons (University of Pennsylvania).7 indexed citations
7.
Wu, Cathy, Aravind Rajeswaran, Yan Duan, et al.. (2018). Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines. arXiv (Cornell University).5 indexed citations
8.
Jain, Prateek, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, & Aaron Sidford. (2018). Accelerating Stochastic Gradient Descent for Least Squares Regression. Conference on Learning Theory. 545–604.5 indexed citations
9.
Kakade, Sham M., et al.. (2018). A Smoother Way to Train Structured Prediction Models. Neural Information Processing Systems. 31. 4766–4778.1 indexed citations
10.
Jain, Prateek, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, & Aaron Sidford. (2016). Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging.. arXiv (Cornell University).4 indexed citations
11.
Jin, Chi, Sham M. Kakade, & Praneeth Netrapalli. (2016). Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent. Neural Information Processing Systems. 29. 4520–4528.15 indexed citations
12.
Belanger, David & Sham M. Kakade. (2015). A Linear Dynamical System Model for Text. International Conference on Machine Learning. 833–842.4 indexed citations
Anandkumar, Animashree, Dean P. Foster, Daniel Hsu, Sham M. Kakade, & Yi-Kai Liu. (2012). Two SVDs Suffice: Spectral decompositions for probabilistic topic modeling and latent Dirichlet allocation. arXiv (Cornell University).9 indexed citations
15.
Kakade, Sham M., et al.. (2010). Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity. ScholarlyCommons (University of Pennsylvania). 9. 381–388.10 indexed citations
16.
Bartlett, Peter L., Varsha Dani, Thomas P. Hayes, et al.. (2008). High-probability regret bounds for bandit online linear optimization. QUT ePrints (Queensland University of Technology). 335–342.32 indexed citations
Kakade, Sham M. & Adam Tauman Kalai. (2005). From Batch to Transductive Online Learning. ScholarlyCommons (University of Pennsylvania). 18. 611–618.8 indexed citations
19.
Kakade, Sham M. & Andrew Y. Ng. (2004). Online Bounds for Bayesian Algorithms. ScholarlyCommons (University of Pennsylvania). 17. 641–648.24 indexed citations
20.
Kakade, Sham M., Yee Whye Teh, & Sam T. Roweis. (2002). An Alternate Objective Function for Markovian Fields. UCL Discovery (University College London). 275–282.37 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.