Niladri S. Chatterji
- Statistics and Probability top 10%
- Artificial Intelligence
- Statistical and Nonlinear Physics
- Computational Mechanics
- Computational Theory and Mathematics
- Co-authors
- Peter L. BartlettXiang ChengMichael I. JordanNicolas FlammarionYi-An MaPhilip M. LongAldo PacchianoBehnam Neyshabur
- Topics
- Markov Chains and Monte Carlo Methods (3 papers)Stochastic Gradient Optimization Techniques (2 papers)Advanced Neuroimaging Techniques and Applications (2 papers)
- Journals
- Journal of Machine Learning ResearchBernoulliInternational Conference on Machine Learning
- Partner nations
- United StatesSwitzerland
In The Last Decade
Niladri S. Chatterji
6 papers receiving 34 citations
Peers
Comparison fields: 5 of 21
- Statistics and Probability 24
- Artificial Intelligence 20
- Statistical and Nonlinear Physics 8
- Computational Mechanics 8
- Computational Theory and Mathematics 7
Countries citing papers authored by Niladri S. Chatterji
This map shows the geographic impact of Niladri S. Chatterji'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 Niladri S. Chatterji with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Niladri S. Chatterji more than expected).
Fields of papers citing papers by Niladri S. Chatterji
This network shows the impact of papers produced by Niladri S. Chatterji. 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 Niladri S. Chatterji. The network helps show where Niladri S. Chatterji may publish in the future.
Co-authorship network of co-authors of Niladri S. Chatterji
This figure shows the co-authorship network connecting the top 25 collaborators of Niladri S. Chatterji. A scholar is included among the top collaborators of Niladri S. Chatterji 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 Niladri S. Chatterji. Niladri S. Chatterji is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | 3 | |
| 2 | 19 | |
| 3 | Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime | 2 |
| 4 | The intriguing role of module criticality in the generalization of deep networks | 3 |
| 5 | Online learning with kernel losses | 2 |
| 6 | Underdamped Langevin MCMC: A non-asymptotic analysis | 9 |
About Niladri S. Chatterji
Niladri S. Chatterji is a scholar working on Statistics and Probability, Computer Science Applications and Artificial Intelligence, having authored 6 papers that have together received 38 indexed citations. Recurring topics across this work include Markov Chains and Monte Carlo Methods (3 papers), Stochastic Gradient Optimization Techniques (2 papers) and Advanced Neuroimaging Techniques and Applications (2 papers). The work is most often cited by research in Statistics and Probability (24 citations), Computational Mathematics (1 citation) and Statistical and Nonlinear Physics (8 citations). Niladri S. Chatterji has collaborated with scholars based in United States and Switzerland. Frequent co-authors include Peter L. Bartlett, Xiang Cheng, Michael I. Jordan, Nicolas Flammarion, Yi-An Ma, Philip M. Long, Aldo Pacchiano, Behnam Neyshabur and Hanie Sedghi. Their work appears in journals such as Journal of Machine Learning Research, Bernoulli and International Conference on Machine Learning.
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.