H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Engineering and Technology H-index 48 Citations 8,312 161 World Ranking 1684 National Ranking 709

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Statistics
  • Machine learning

Barnabás Póczos focuses on Artificial intelligence, Algorithm, Gradient descent, Mathematical optimization and Artificial neural network. His Artificial intelligence research incorporates themes from Machine learning, Invariant and Permutation. His Communication complexity study in the realm of Algorithm interacts with subjects such as Speedup.

His Gradient descent study combines topics in areas such as Kernel, Kernel and Variance reduction. In his research, Structure formation, Universe and Statistical physics is intimately related to Structure, which falls under the overarching field of Mathematical optimization. His Artificial neural network research is multidisciplinary, relying on both Cross-validation, Inverse problem, Metric, Inpainting and Compressed sensing.

His most cited work include:

  • Deep Sets (401 citations)
  • Gradient Descent Provably Optimizes Over-parameterized Neural Networks (323 citations)
  • Deep Sets (278 citations)

What are the main themes of his work throughout his whole career to date?

Barnabás Póczos mainly investigates Artificial intelligence, Machine learning, Algorithm, Applied mathematics and Estimator. The Artificial intelligence study combines topics in areas such as Galaxy and Pattern recognition. Barnabás Póczos has researched Algorithm in several fields, including Subspace topology, Independent component analysis, Density estimation, Reproducing kernel Hilbert space and Entropy.

His work deals with themes such as Smoothness, Probability distribution, Kernel density estimation and Mathematical optimization, which intersect with Applied mathematics. His Bayesian optimization study in the realm of Mathematical optimization connects with subjects such as Fidelity. His studies examine the connections between Estimator and genetics, as well as such issues in Nonparametric statistics, with regards to Parametric statistics.

He most often published in these fields:

  • Artificial intelligence (37.62%)
  • Machine learning (19.94%)
  • Algorithm (17.04%)

What were the highlights of his more recent work (between 2018-2021)?

  • Artificial intelligence (37.62%)
  • Machine learning (19.94%)
  • Benchmark (4.50%)

In recent papers he was focusing on the following fields of study:

Barnabás Póczos mostly deals with Artificial intelligence, Machine learning, Benchmark, Applied mathematics and Estimator. His study in Artificial intelligence is interdisciplinary in nature, drawing from both Natural language processing and Pattern recognition. His Machine learning research incorporates elements of Inference and Bayesian probability, Bayesian inference.

His Applied mathematics research is multidisciplinary, incorporating elements of Probability distribution, Total variation, Empirical distribution function and Minimax. His Estimator study combines topics from a wide range of disciplines, such as Galaxy cluster, Statistical model, Power law and Joint probability distribution. His Kernel study incorporates themes from Theoretical computer science and Mathematical optimization.

Between 2018 and 2021, his most popular works were:

  • Learning to predict the cosmological structure formation. (77 citations)
  • Characterizing and Avoiding Negative Transfer (76 citations)
  • Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels (66 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Statistics
  • Machine learning

His primary areas of investigation include Artificial intelligence, Machine learning, Heuristics, Artificial neural network and Hyperparameter. His Artificial intelligence research includes themes of Large Hadron Collider, Detector and Natural language processing. His research in Machine learning intersects with topics in Transformation, Sampling, Simple and Image.

His Heuristics research focuses on Reinforcement learning and how it relates to Feature selection, Boolean satisfiability problem, Heuristic and Local search. His work carried out in the field of Artificial neural network brings together such families of science as Bayesian probability and Bayesian inference. His Deep learning research is multidisciplinary, incorporating perspectives in Transfer of learning, Data mining and Range.

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.

Top Publications

Deep Sets

Manzil Zaheer;Satwik Kottur;Siamak Ravanbakhsh;Barnabas Poczos.
arXiv: Learning (2017)

483 Citations

Gradient Descent Provably Optimizes Over-parameterized Neural Networks

Simon S. Du;Xiyu Zhai;Barnabas Poczos;Aarti Singh.
arXiv: Learning (2018)

323 Citations

MMD GAN: Towards Deeper Understanding of Moment Matching Network

Chun-Liang Li;Wei-Cheng Chang;Yu Cheng;Yiming Yang.
neural information processing systems (2017)

247 Citations

One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models

J. H. Rick Chang;Chun-Liang Li;Barnabas Poczos;B. V. K. Vijaya Kumar.
international conference on computer vision (2017)

241 Citations

Stochastic Variance Reduction for Nonconvex Optimization

Sashank J. Reddi;Ahmed Hefny;Suvrit Sra;Barnabás Póczós.
arXiv: Optimization and Control (2016)

197 Citations

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

Kirthevasan Kandasamy;Willie Neiswanger;Jeff Schneider;Barnabas Poczos.
neural information processing systems (2018)

169 Citations

Estimation of Rényi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs

Dávid Pál;Barnabás Póczos;Csaba Szepesvári.
neural information processing systems (2010)

158 Citations

Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization

Sashank J. Reddi;Suvrit Sra;Barnabas Poczos;Alexander J. Smola.
neural information processing systems (2016)

156 Citations

Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima

Simon S. Du;Jason D. Lee;Yuandong Tian;Barnabas Poczos.
international conference on machine learning (2018)

146 Citations

Gradient Descent Can Take Exponential Time to Escape Saddle Points

Simon S. Du;Chi Jin;Jason D. Lee;Michael I. Jordan.
neural information processing systems (2017)

141 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

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

Contact us

Top Scientists Citing Barnabás Póczos

Quanquan Gu

Quanquan Gu

University of California, Los Angeles

Publications: 46

Michael I. Jordan

Michael I. Jordan

University of California, Berkeley

Publications: 34

Alfred O. Hero

Alfred O. Hero

University of Michigan–Ann Arbor

Publications: 33

Louis-Philippe Morency

Louis-Philippe Morency

Carnegie Mellon University

Publications: 25

Tianbao Yang

Tianbao Yang

University of Iowa

Publications: 25

Jason D. Lee

Jason D. Lee

Princeton University

Publications: 23

Peter Richtárik

Peter Richtárik

King Abdullah University of Science and Technology

Publications: 23

Ruslan Salakhutdinov

Ruslan Salakhutdinov

Carnegie Mellon University

Publications: 23

Heng Huang

Heng Huang

University of Pittsburgh

Publications: 20

arthur gretton

arthur gretton

University College London

Publications: 20

Yee Whye Teh

Yee Whye Teh

University of Oxford

Publications: 20

Max Welling

Max Welling

University of Amsterdam

Publications: 18

Suvrit Sra

Suvrit Sra

MIT

Publications: 18

Dacheng Tao

Dacheng Tao

University of Sydney

Publications: 17

Andreas Krause

Andreas Krause

ETH Zurich

Publications: 16

Something went wrong. Please try again later.