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.
Deep Learning with Differential Privacy
20163.0k citationsIlya Mironov, Kunal Talwar et al.arXiv (Cornell University)profile →
This map shows the geographic impact of Kunal Talwar'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 Kunal Talwar with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Kunal Talwar more than expected).
This network shows the impact of papers produced by Kunal Talwar. 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 Kunal Talwar. The network helps show where Kunal Talwar may publish in the future.
Co-authorship network of co-authors of Kunal Talwar
This figure shows the co-authorship network connecting the top 25 collaborators of Kunal Talwar.
A scholar is included among the top collaborators of Kunal Talwar 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 Kunal Talwar. Kunal Talwar 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.
Feldman, Vitaly, et al.. (2021). Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry. International Conference on Machine Learning. 393–403.3 indexed citations
2.
Jiang, Ziheng, Chiyuan Zhang, Kunal Talwar, & Michael C. Mozer. (2021). Characterizing Structural Regularities of Labeled Data in Overparameterized Models. International Conference on Machine Learning. 5034–5044.7 indexed citations
3.
Jiang, Ziheng, Chiyuan Zhang, Kunal Talwar, & Michael C. Mozer. (2020). Exploring the Memorization-Generalization Continuum in Deep Learning. arXiv (Cornell University).2 indexed citations
Schmidt, Ludwig, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, & Aleksander Mądry. (2018). Adversarially Robust Generalization Requires More Data. DSpace@MIT (Massachusetts Institute of Technology). 31. 5014–5026.56 indexed citations
6.
Papernot, Nicolas, Shuang Song, Ilya Mironov, et al.. (2018). Scalable Private Learning with PATE. arXiv (Cornell University).22 indexed citations
7.
Daniely, Amit, Nevena Lazic, Yoram Singer, & Kunal Talwar. (2017). Short and Deep: Sketching and Neural Networks. International Conference on Learning Representations.2 indexed citations
8.
Talwar, Kunal, Abhradeep Thakurta, & Li Zhang. (2015). Nearly-optimal private LASSO. Neural Information Processing Systems. 28. 3025–3033.35 indexed citations
9.
Krauthgamer, Robert, Joseph Naor, Roy Schwartz, & Kunal Talwar. (2014). Non-uniform graph partitioning. Symposium on Discrete Algorithms. 1229–1243.3 indexed citations
10.
Dwork, Cynthia, Kunal Talwar, Abhradeep Thakurta, & Li Zhang. (2014). Analyze Gauss: optimal bounds for privacy-preserving PCA.1 indexed citations
Shankar, Umesh, Kunal Talwar, Jeffrey S. Foster, & David Wagner. (2001). Detecting format string vulnerabilities with type qualifiers. USENIX Security Symposium. 16–16.257 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.