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.
Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
Citations per year, relative to Mikhail Belkin Mikhail Belkin (= 1×)
peers
Ivor W. Tsang
Countries citing papers authored by Mikhail Belkin
Since
Specialization
Citations
This map shows the geographic impact of Mikhail Belkin'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 Mikhail Belkin with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Mikhail Belkin more than expected).
This network shows the impact of papers produced by Mikhail Belkin. 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 Mikhail Belkin. The network helps show where Mikhail Belkin may publish in the future.
Co-authorship network of co-authors of Mikhail Belkin
This figure shows the co-authorship network connecting the top 25 collaborators of Mikhail Belkin.
A scholar is included among the top collaborators of Mikhail Belkin 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 Mikhail Belkin. Mikhail Belkin is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Liu, Chaoyue, et al.. (2020). On the linearity of large non-linear models: when and why the tangent kernel is constant. arXiv (Cornell University). 33. 15954–15964.1 indexed citations
4.
Liu, Chaoyue & Mikhail Belkin. (2020). Accelerating SGD with momentum for over-parameterized learning. International Conference on Learning Representations.2 indexed citations
5.
Belkin, Mikhail, et al.. (2018). MaSS: an Accelerated Stochastic Method for Over-parametrized Learning.. arXiv (Cornell University).1 indexed citations
6.
Belkin, Mikhail, Daniel Hsu, & Partha P. Mitra. (2018). Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate. Cold Spring Harbor Laboratory Institutional Repository (Cold Spring Harbor Laboratory). 31. 2300–2311.15 indexed citations
7.
Belkin, Mikhail, Daniel Hsu, Siyuan Ma, & Soumik Mandal. (2018). Reconciling modern machine learning and the bias-variance trade-off. arXiv (Cornell University).34 indexed citations
8.
Ma, Siyuan, Raef Bassily, & Mikhail Belkin. (2018). The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning. International Conference on Machine Learning. 3325–3334.20 indexed citations
9.
Ma, Siyuan & Mikhail Belkin. (2017). Diving into the shallows: a computational perspective on large-scale shallow learning. Neural Information Processing Systems. 30. 3778–3787.4 indexed citations
10.
Belkin, Mikhail & V. Iakovlev. (2016). Wafer fused long-wavelength VCSELs for analog photonics applications.2 indexed citations
11.
Belkin, Mikhail, et al.. (2016). Clustering with Bregman Divergences: an Asymptotic Analysis. Neural Information Processing Systems. 29. 2343–2351.4 indexed citations
12.
Belkin, Mikhail, et al.. (2014). Learning with Fredholm Kernels. Neural Information Processing Systems. 27. 2951–2959.7 indexed citations
13.
Belkin, Mikhail & K. P. Sinha. (2010). Toward Learning Gaussian Mixtures with Arbitrary Separation.. Conference on Learning Theory. 407–419.9 indexed citations
14.
Sreekumar, Vishnu, et al.. (2010). The dimensionality of episodic images. eScholarship (California Digital Library). 32(32).1 indexed citations
15.
Sinha, K. P. & Mikhail Belkin. (2007). The Value of Labeled and Unlabeled Examples when the Model is Imperfect. Neural Information Processing Systems. 20. 1361–1368.12 indexed citations
Altün, Yasemin, David McAllester, & Mikhail Belkin. (2005). Maximum Margin Semi-Supervised Learning for Structured Variables. MPG.PuRe (Max Planck Society). 18. 33–40.70 indexed citations
18.
Altün, Yasemin, David McAllester, & Mikhail Belkin. (2005). Margin Semi-Supervised Learning for Structured Variables.. Neural Information Processing Systems. 33–40.6 indexed citations
19.
Belkin, Mikhail & Partha Niyogi. (2002). Using manifold structure for partially labelled classification. Neural Information Processing Systems. 953–960.63 indexed citations
20.
Belkin, Mikhail & Partha Niyogi. (2002). Using Manifold Stucture for Partially Labeled Classification. Neural Information Processing Systems. 15. 953–960.43 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.