World's Best Scientists 2026 revealed!

Overview

Anatoli Juditsky is affiliated with Grenoble Alpes University in France and has a research profile centered on mathematics, engineering, and computer science. Their work spans multiple subfields including statistics and probability, computational mechanics, computer vision and pattern recognition, radiology, nuclear medicine and imaging, and applied mathematics.

The scientist's research addresses a range of topics, particularly emphasizing sparse and compressive sensing techniques, statistical methods and inference, image and signal denoising methods, medical imaging techniques and applications, statistical and numerical algorithms, numerical methods in inverse problems, and advanced optimization algorithms research.

Juditsky has published extensively with notable frequent co-authors, including Arkadi Nemirovski, Yannis Bekri, Sasila Ilandarideva, Guanghui Lan, and Tianjiao Li.

The publication venues where their work commonly appears are:

  • arXiv (Cornell University)
  • Mathematical Programming
  • Open Journal of Mathematical Optimization
  • Journal of Optimization Theory and Applications
  • Optimization methods & software

Recent papers include:

  • Unifying mirror descent and dual averaging, 2022, Mathematical Programming
  • On well-structured convex-concave saddle point problems and variational inequalities with monotone operators, 2021, Optimization methods & software
  • Accelerated stochastic approximation with state-dependent noise, 2024, Mathematical Programming
  • On Well-Structured Convex-Concave Saddle Point Problems and Variational Inequalities with Monotone Operators, 2021, arXiv (Cornell University)
  • Hypothesis testing via Euclidean separation, 2020, Annales de l Institut Henri Poincaré Probabilités et Statistiques

Juditsky has also contributed to academic literature by authoring a book titled Statistical Inference via Convex Optimization, published in 2020 by Princeton University Press.

Best Publications

  • Nonlinear black-box modeling in system identification: a unified overview

    Jonas Sjöberg;Qinghua Zhang;Lennart Ljung;Albert Benveniste

  • Robust Stochastic Approximation Approach to Stochastic Programming

    A. Nemirovski;A. Juditsky;G. Lan;A. Shapiro

  • Stochastic Approximation approach to Stochastic Programming

    Anatoli Juditsky;Guanghui Lan;Arkadii S. Nemirovski;Alexander Shapiro

  • Acceleration of stochastic approximation by averaging

    B. T. Polyak;A. B. Juditsky

  • Nonlinear black-box models in system identification: mathematical foundations

    Anatoli Juditsky;Håkan Hjalmarsson;Albert Benveniste;Bernard Delyon

  • Accuracy analysis for wavelet approximations

    B. Delyon;A. Juditsky;A. Benveniste

  • Direct estimation of the index coefficient in a single-index model

    Marian Hristache;Anatoli Juditsky;Vladimir Spokoiny

  • Solving variational inequalities with stochastic mirror-prox algorithm

    Anatoli Juditsky;Arkadii S. Nemirovski;Claire Tauvel

  • Functional aggregation for nonparametric regression

    Anatoli Juditsky;Arkadii Nemirovski

  • Structure Adaptive Approach for Dimension Reduction

    Marian Hristache;Anatoli Juditsky;Jörg Polzehl;Vladimir Spokoiny

  • Conditional gradient algorithms for norm-regularized smooth convex optimization

    Zaid Harchaoui;Anatoli Juditsky;Arkadi Nemirovski

  • First Order Methods for Nonsmooth Convex Large-Scale Optimization, I: General Purpose Methods

    Anatoli Juditsky;Arkadii S. Nemirovski

  • Learning by mirror averaging

    Anatoli Juditsky;Philippe Rigollet;Alexandre Tsybakov

  • On Minimax Wavelet Estimators

    B. Delyon;A. Juditsky

  • Solving variational inequalities with Stochastic Mirror-Prox algorithm

    Anatoli Juditsky;Arkadii S. Nemirovskii;Claire Tauvel

  • On verifiable sufficient conditions for sparse signal recovery via ℓ 1 minimization

    Anatoli Juditsky;Arkadi Nemirovski

  • Recursive Aggregation of Estimators by the Mirror Descent Algorithm with Averaging

    A. B. Juditsky;A. V. Nazin;A. B. Tsybakov;N. Vayatis

  • Deterministic and Stochastic Primal-Dual Subgradient Algorithms for Uniformly Convex Minimization

    Anatoli Juditsky;Yuri Nesterov

  • Accelerated Stochastic Approximation

    Bernard Delyon;Anatoli B. Juditsky

  • On Low Rank Matrix Approximations with Applications to Synthesis Problem in Compressed Sensing

    Anatoli Juditsky;Fatma Kilinc Karzan;Arkadii S. Nemirovski

Frequent Co-Authors

Arkadi Nemirovski
Arkadi Nemirovski Georgia Institute of Technology
Alexandre B. Tsybakov
Alexandre B. Tsybakov École Nationale de la Statistique et de l'Administration Économique
Vladimir Spokoiny
Vladimir Spokoiny Weierstrass Institute for Applied Analysis and Stochastics
Albert Benveniste
Albert Benveniste French Institute for Research in Computer Science and Automation - INRIA
Zaid Harchaoui
Zaid Harchaoui University of Washington
Lennart Ljung
Lennart Ljung Linköping University
Jonas Sjöberg
Jonas Sjöberg Chalmers University of Technology
Håkan Hjalmarsson
Håkan Hjalmarsson Royal Institute of Technology
Alexander Shapiro
Alexander Shapiro Georgia Institute of Technology

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

For students pursuing Mathematics in the USA, exploring related online degrees can open diverse career opportunities. Many professionals complement their math background with business knowledge, making programs like 1 year MBA programs an appealing choice. These accelerated degrees offer a balance between advanced math skills and essential business acumen.

When considering an MBA, understanding the option to transfer prior credits can save both time and tuition fees. Several universities provide flexible pathways, as highlighted in mba transfer credits options, making advanced studies more accessible for math graduates switching fields.

Data analytics stands out as a natural extension of a math degree. The surge in demand for data scientists means that programs such as the best masters in data analytics programs are highly sought after. These degrees sharpen analytical skills and open pathways into tech, finance, and healthcare sectors.

For those aiming for less competitive yet practical MBA specializations, identifying the easiest MBA specialization can provide a strategic advantage. This approach enables math graduates to quickly gain managerial skills and broaden career options with a manageable commitment.

Best Scientists Citing Anatoli Juditsky

Trending Scientists

Recently Published Articles