World's Best Scientists 2026 revealed!
Balaji Lakshminarayanan

Balaji Lakshminarayanan

D-Index & Metrics

Computer Science

D-Index
36
Citations
15361
World Ranking
10964
National Ranking
4558

Overview

Balaji Lakshminarayanan is affiliated with Google in the United States and works primarily in the field of Computer Science. Their research spans various specialized subfields, including Artificial Intelligence, Computer Vision and Pattern Recognition, Global and Planetary Change, Water Science and Technology, and Control and Systems Engineering.

The scientist's scholarly contributions focus on multiple main topics:

  • Adversarial Robustness in Machine Learning
  • Anomaly Detection Techniques and Applications
  • Domain Adaptation and Few-Shot Learning
  • Advanced Neural Network Applications
  • Machine Learning and Data Classification
  • Topic Modeling
  • Flood Risk Assessment and Management

Balaji Lakshminarayanan has authored numerous papers, with a notable concentration of publications in arXiv (Cornell University). Other venues include Environmental Science and Pollution Research, Machine Learning, Journal of Water and Climate Change, and Medical Image Analysis.

Recent publications include:

  • "Gemini: A Family of Highly Capable Multimodal Models" (2023) published in arXiv (Cornell University)
  • "Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness" (2020) published in arXiv (Cornell University)
  • "Exploring the Limits of Out-of-Distribution Detection" (2021) published in arXiv (Cornell University)
  • "Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift" (2020) published in arXiv (Cornell University)

The scientist frequently collaborates with other researchers, with notable co-authors such as Dustin Tran, Jie Ren, Jasper Snoek, Jeremiah Zhe Liu, and Shreyas Padhy. Their co-authorship counts indicate strong collaborative relationships, particularly with Dustin Tran and Jie Ren.

Best Publications

  • Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

    Balaji Lakshminarayanan;Alexander Pritzel;Charles Blundell

  • Clinically applicable deep learning for diagnosis and referral in retinal disease

    Jeffrey De Fauw;Joseph R. Ledsam;Bernardino Romera-Paredes;Stanislav Nikolov

  • Normalizing flows for probabilistic modeling and inference

    George Papamakarios;Eric T. Nalisnick;Danilo Jimenez Rezende;Shakir Mohamed

  • Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

    Unknown

  • Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift

    Yaniv Ovadia;Emily Fertig;Jie Ren;Zachary Nado

  • AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

    Dan Hendrycks;Norman Mu;Ekin Dogus Cubuk;Barret Zoph

  • Do Deep Generative Models Know What They Don't Know?

    Eric T. Nalisnick;Akihiro Matsukawa;Yee Whye Teh;Dilan Görür

  • Deep Ensembles: A Loss Landscape Perspective

    Stanislav Fort;Huiyi Hu;Balaji Lakshminarayanan

  • Likelihood Ratios for Out-of-Distribution Detection

    Jie Ren;Peter J. Liu;Emily Amanda Fertig;Jasper Roland Snoek

  • Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach

    Forrest Briggs;Balaji Lakshminarayanan;Lawrence Neal;Xiaoli Z. Fern

  • Variational Approaches for Auto-Encoding Generative Adversarial Networks.

    Mihaela Rosca;Balaji Lakshminarayanan;David Warde-Farley;Shakir Mohamed

  • The Cramer Distance as a Solution to Biased Wasserstein Gradients

    Marc G. Bellemare;Ivo Danihelka;Will Dabney;Shakir Mohamed

  • Learning in Implicit Generative Models

    Shakir Mohamed;Balaji Lakshminarayanan

  • Mondrian Forests: Efficient Online Random Forests

    Balaji Lakshminarayanan;Daniel M Roy;Yee Whye Teh

  • Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

    William Fedus;Mihaela Rosca;Balaji Lakshminarayanan;Andrew M. Dai

  • Adapting Auxiliary Losses Using Gradient Similarity

    Yunshu Du;Wojciech M. Czarnecki;Siddhant M. Jayakumar;Razvan Pascanu

  • Plex: Towards Reliability using Pretrained Large Model Extensions

    Unknown

  • Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

    Jeremiah Zhe Liu;Zi Lin;Shreyas Padhy;Dustin Tran

  • Exploring the Limits of Out-of-Distribution Detection

    Stanislav Fort;Jie Ren;Balaji Lakshminarayanan

  • Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift

    Zachary Nado;Shreyas Padhy;D. Sculley;Alexander D'Amour

  • Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality

    Eric Nalisnick;Akihiro Matsukawa;Yee Whye Teh;Balaji Lakshminarayanan

  • Does your dermatology classifier know what it doesn't know? Detecting the long-tail of unseen conditions.

    Abhijit Guha Roy;Jie Ren;Shekoofeh Azizi;Aaron Loh

  • Bayesian Deep Ensembles via the Neural Tangent Kernel

    Bobby He;Balaji Lakshminarayanan;Yee Whye Teh

Frequent Co-Authors

Yee Whye Teh
Yee Whye Teh University of Oxford
Jasper Snoek
Jasper Snoek Google (United States)
Dustin Tran
Dustin Tran Google (United States)
D. Sculley
D. Sculley Google (United States)
Charles Blundell
Charles Blundell DeepMind (United Kingdom)
Arthur Gretton
Arthur Gretton University College London
Nicolas Heess
Nicolas Heess DeepMind (United Kingdom)
Razvan Pascanu
Razvan Pascanu DeepMind (United Kingdom)
András György
András György New York University Abu Dhabi
Ian Goodfellow
Ian Goodfellow Google (United States)

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 Computer Science doesn't mean you have to follow a single path. Many students opt for fast, flexible online options to launch or elevate their tech careers. There are quick certifications that pay well in tech that can be completed within months, teaching in-demand skills like cybersecurity basics or data analytics.

For those seeking an advanced credential, consider quick masters degrees online. These programs let you earn a respected master's in computer science or IT-related fields, often within a year—ideal for busy professionals or recent graduates looking to specialize further.

You may also want to explore the most useful graduate degrees matched to current job market needs. Tech-oriented master's programs stand out for their high ROI and employment opportunities, from artificial intelligence to software engineering.

Not ready for a full bachelor's or master’s? An associates degree online offers a practical, affordable entry into computer science. These programs are ideal if you want to start working faster while building a strong technical foundation.

Best Scientists Citing Balaji Lakshminarayanan

Trending Scientists

Recently Published Articles