World's Best Scientists 2026 revealed!

D-Index & Metrics

Engineering and Technology

D-Index
65
Citations
13947
World Ranking
1546
National Ranking
505

Overview

Barnabás Póczos is affiliated with Carnegie Mellon University in the United States. Their research is primarily situated within the field of Computer Science, with a significant focus on Artificial Intelligence. Other subfields of study include Molecular Biology, Computer Vision and Pattern Recognition, Computational Mechanics, and Materials Chemistry.

Their work covers a range of topics including:

  • Topic Modeling
  • Natural Language Processing Techniques
  • Sparse and Compressive Sensing Techniques
  • Domain Adaptation and Few-Shot Learning
  • Machine Learning in Materials Science
  • Cell Image Analysis Techniques
  • Multimodal Machine Learning Applications

Frequent coauthors collaborating with Barnabás Póczos include:

  • Newell R. Washburn
  • Emmanouil Antonios Platanios
  • Siamak Ravanbakhsh
  • Chunliang Li
  • Euxhen Hasanaj

Publication venues where Barnabás Póczos has frequently contributed are:

  • arXiv (Cornell University)
  • bioRxiv (Cold Spring Harbor Laboratory)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zenodo (CERN European Organization for Nuclear Research)
  • Cell Reports Physical Science

Recent papers authored or coauthored by Barnabás Póczos include:

  • Autonomous Discovery of Battery Electrolytes with Robotic Experimentation and Machine Learning, 2020, Cell Reports Physical Science
  • Hierarchical Machine Learning for High-Fidelity 3D Printed Biopolymers, 2020, ACS Biomaterials Science & Engineering
  • Deep generative models for galaxy image simulations, 2021, Monthly Notices of the Royal Astronomical Society
  • Diffusion Models in De Novo Drug Design, 2024, Journal of Chemical Information and Modeling
  • End-to-end jet classification of quarks and gluons with the CMS Open Data, 2020, Nuclear Instruments and Methods in Physics Research Section A Accelerators Spectrometers Detectors and Associated Equipment

Best Publications

  • Deep Sets

    Manzil Zaheer;Satwik Kottur;Siamak Ravanbakhsh;Barnabas Poczos

  • Gradient Descent Provably Optimizes Over-parameterized Neural Networks

    Simon S. Du;Xiyu Zhai;Barnabas Poczos;Aarti Singh

  • MMD GAN: Towards Deeper Understanding of Moment Matching Network

    Chun-Liang Li;Wei-Cheng Chang;Yu Cheng;Yiming Yang

  • Stochastic variance reduction for nonconvex optimization

    Sashank J. Reddi;Ahmed Hefny;Suvrit Sra;Barnabás Póczós

  • Neural Architecture Search with Bayesian Optimisation and Optimal Transport

    Kirthevasan Kandasamy;Willie Neiswanger;Jeff Schneider;Barnabas Poczos

  • Characterizing and Avoiding Negative Transfer

    Zirui Wang;Zihang Dai;Barnabas Poczos;Jaime Carbonell

  • Found in Translation: Learning Robust Joint Representations by Cyclic Translations between Modalities

    Hai Pham;Paul Pu Liang;Thomas Manzini;Louis-Philippe Morency

  • 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

  • Competence-based Curriculum Learning for Neural Machine Translation

    Emmanouil Antonios Platanios;Otilia Stretcu;Graham Neubig;Barnabás Póczos

  • High Dimensional Bayesian Optimisation and Bandits via Additive Models

    Kirthevasan Kandasamy;Jeff Schneider;Barnabas Poczos

  • CMU DeepLens: deep learning for automatic image-based galaxy-galaxy strong lens finding

    Francois Lanusse;Quanbin Ma;Nan Li;Nan Li;Thomas E. Collett

  • Learning to predict the cosmological structure formation.

    Siyu He;Yin Li;Yu Feng;Yu Feng;Shirley Ho

  • Gradient Descent Can Take Exponential Time to Escape Saddle Points

    Simon S. Du;Chi Jin;Jason D. Lee;Michael I. Jordan

  • Predicting enhancer-promoter interaction from genomic sequence with deep neural networks

    Shashank Singh;Yang Yang;Barnabás Póczos;Jian Ma

  • Proximal stochastic methods for nonsmooth nonconvex finite-sum optimization

    Sashank J. Reddi;Suvrit Sra;Barnabas Poczos;Alexander J. Smola

  • Quantifying Differences and Similarities in Whole-Brain White Matter Architecture Using Local Connectome Fingerprints.

    Fang-Cheng Yeh;Jean M. Vettel;Aarti Singh;Barnabás Póczos

  • On the decreasing power of kernel and distance based nonparametric hypothesis tests in high dimensions

    Aaditya Ramdas;Sashank J. Reddi;Barnabás Póczos;Aarti Singh

  • On variance reduction in stochastic gradient descent and its asynchronous variants

    Sashank J. Reddi;Ahmed Hefny;Suvrit Sra;Barnabás Pöczos

  • 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

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

    Dávid Pál;Barnabás Póczos;Csaba Szepesvári

  • Parallelised Bayesian Optimisation via Thompson Sampling

    Kirthevasan Kandasamy;Akshay Krishnamurthy;Jeff Schneider;Barnabás Póczos

  • Multi-fidelity Bayesian optimisation with continuous approximations

    Kirthevasan Kandasamy;Gautam Dasarathy;Jeff Schneider;Barnabás Póczos

  • Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

    Simon S. Du;Kangcheng Hou;Russ R. Salakhutdinov;Barnabas Poczos

Frequent Co-Authors

Jeff Schneider
Jeff Schneider Carnegie Mellon University
Aarti Singh
Aarti Singh Carnegie Mellon University
Sashank J. Reddi
Sashank J. Reddi Google (United States)
Arthur Gretton
Arthur Gretton University College London
Eric P. Xing
Eric P. Xing Mohamed bin Zayed University of Artificial Intelligence
Alexander J. Smola
Alexander J. Smola Amazon (United States)
Larry Wasserman
Larry Wasserman Carnegie Mellon University
Simon S. Du
Simon S. Du University of Washington
Ruslan Salakhutdinov
Ruslan Salakhutdinov Carnegie Mellon University

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

Exploring online education can open diverse paths within Engineering and Technology, as well as related fields. Flexible online programs allow students to gain practical skills and credentials at their own pace, from anywhere in the world.

For example, if you’re interested in the business side of sports or facility management, pursuing a sports management degree online can prepare you for leadership roles in the multi-billion-dollar sports industry. Urban infrastructure is also a rapidly growing field; enrolling in an urban planning degree online equips graduates to help design smarter, more sustainable cities.

If you already have a bachelor’s degree, accelerated postgraduate options are available. A master's degree in 6 months online can help you upskill quickly and advance your career without a lengthy commitment.

Additionally, for those seeking specialized expertise or career advancement without a four-year degree, there are numerous certificate programs that provide targeted training and higher earning potential. With so many online degree and certificate options, students can align their studies with their professional goals in Engineering, Technology, and beyond.

Best Scientists Citing Barnabás Póczos

Trending Scientists

Recently Published Articles