What is he best known for?
The fields of study he is best known for:
- Statistics
- Machine learning
- Artificial intelligence
His main research concerns Mathematical optimization, Probability distribution, Computation, Regularization and Algorithm.
He studies Linear programming which is a part of Mathematical optimization.
His studies in Computation integrate themes in fields like Metric, Iterative proportional fitting and Probability measure.
His Probability measure research incorporates elements of Smoothing, Dimension and Convex optimization.
His study in Regularization is interdisciplinary in nature, drawing from both Function, Reproducing kernel Hilbert space and Maximization.
His Algorithm research includes elements of Differentiable function, Dynamic time warping, Geodesic and Heat kernel.
His most cited work include:
- Sinkhorn Distances: Lightspeed Computation of Optimal Transport (1137 citations)
- Computational Optimal Transport (529 citations)
- Iterative Bregman Projections for Regularized Transportation Problems (416 citations)
What are the main themes of his work throughout his whole career to date?
His scientific interests lie mostly in Algorithm, Regularization, Differentiable function, Artificial intelligence and Mathematical optimization.
Series is closely connected to Dynamic time warping in his research, which is encompassed under the umbrella topic of Algorithm.
His Regularization research is multidisciplinary, relying on both Regression, Entropy and Applied mathematics.
His Differentiable function research integrates issues from Smoothing, Probability distribution, Function and Sorting.
His Mathematical optimization research includes themes of Computation and Metric.
His research integrates issues of Entropy and Probability measure in his study of Computation.
He most often published in these fields:
- Algorithm (32.64%)
- Regularization (30.56%)
- Differentiable function (20.83%)
What were the highlights of his more recent work (between 2019-2021)?
- Regularization (30.56%)
- Differentiable function (20.83%)
- Mathematical optimization (18.06%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Regularization, Differentiable function, Mathematical optimization, Applied mathematics and Linear programming.
The Regularization study combines topics in areas such as Linear regression, Regression, Kernel, Space and Entropy.
His work deals with themes such as Smoothing, Algorithm and Matrix, which intersect with Differentiable function.
His research in Mathematical optimization intersects with topics in Sorting, Structured prediction, Smoothness and Computation.
His studies deal with areas such as Dimension, Covariance, Closed-form expression and Curse of dimensionality as well as Applied mathematics.
His Linear programming study also includes
- Flow together with Probability measure, Fast algorithm, Real image and Efficient algorithm,
- Representation that connect with fields like Point.
Between 2019 and 2021, his most popular works were:
- Learning with Differentiable Perturbed Optimizers. (17 citations)
- Projection Robust Wasserstein Distance and Riemannian Optimization (10 citations)
- Entropic Optimal Transport between (Unbalanced) Gaussian Measures has a Closed Form (10 citations)
In his most recent research, the most cited papers focused on:
- Statistics
- Machine learning
- Artificial intelligence
Marco Cuturi mostly deals with Regularization, Differentiable function, Applied mathematics, Degenerate energy levels and Gaussian.
His work often combines Regularization and Electromagnetic field studies.
His Differentiable function study combines topics in areas such as Sorting, Smoothness, Structured prediction and Constant.
The concepts of his Applied mathematics study are interwoven with issues in Projection, Riemannian optimization, Computation and Theory of computation.
Degenerate energy levels is intertwined with Closed-form expression, Covariance, Mass transportation, Numerical resolution and Extension in his research.
While working on this project, he studies both Gaussian and Intersection.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
