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.
A Hybrid Approach to Privacy-Preserving Federated Learning
Countries citing papers authored by Thomas Steinke
Since
Specialization
Citations
This map shows the geographic impact of Thomas Steinke'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 Thomas Steinke with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Thomas Steinke more than expected).
This network shows the impact of papers produced by Thomas Steinke. 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 Thomas Steinke. The network helps show where Thomas Steinke may publish in the future.
Co-authorship network of co-authors of Thomas Steinke
This figure shows the co-authorship network connecting the top 25 collaborators of Thomas Steinke.
A scholar is included among the top collaborators of Thomas Steinke 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 Thomas Steinke. Thomas Steinke is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Liu, Terrance, et al.. (2021). Leveraging Public Data for Practical Private Query Release. International Conference on Machine Learning. 6968–6977.7 indexed citations
4.
Steinke, Thomas, et al.. (2021). Evading the Curse of Dimensionality in Unconstrained Private GLMs. International Conference on Artificial Intelligence and Statistics. 2638–2646.5 indexed citations
5.
Steinke, Thomas, et al.. (2020). Open Problem: Information Complexity of VC Learning. Conference on Learning Theory. 3857–3863.1 indexed citations
6.
Wood, Alexandra, Micah Altman, Mark Bun, et al.. (2018). Differential Privacy: A Primer for a Non-Technical Audience. Digital Access to Scholarship at Harvard (DASH) (Harvard University). 21(1). 209.13 indexed citations
7.
Nissim, Kobbi, Alexandra Wood, Mark Bun, et al.. (2018). Bridging the Gap between Computer Science and Legal Approaches to Privacy. Digital Access to Scholarship at Harvard (DASH) (Harvard University). 31(2). 687.24 indexed citations
8.
Ullman, Jonathan, Adam Smith, Kobbi Nissim, Uri Stemmer, & Thomas Steinke. (2018). The Limits of Post-Selection Generalization. Neural Information Processing Systems. 31. 6400–6409.2 indexed citations
Sainudiin, Raazesh & Thomas Steinke. (2013). A Rigorous Extension of the Schönhage-Strassen Integer Multiplication Algorithm Using Complex Interval Arithmetic.. Reliable Computing. 18. 97–116.1 indexed citations
13.
Steinke, Thomas. (2012). Pseudorandomness for Permutation Branching Programs Without the Group Theory.. Electronic colloquium on computational complexity. 19. 83.15 indexed citations
Schmidt, Christian, Thomas Steinke, Stefan Moritz, Bernhard Gräf, & Michael Bucher. (2010). Akutes Nierenversagen und Sepsis. Der Anaesthesist. 59(8). 682–699.1 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.