Sotabase

Career

· Researcher, Google DeepMind2022–
· Applied Scientist Intern, Amazon2021–2021
· Research Intern, Google2020–2020
· Research Intern, Microsoft New England Research and Development Center2018–2018
· Doctor of Philosophy - PhD, Machine Learning, University of California, Berkeley2016–2022
· Master of Philosophy - MPhil, Information Engineering: Machine Learning, University of Cambridge2014–2016
· Machine Learning Engineer Intern, Diffeo2013–2014
· Bachelor of Arts (B.A.), Theoretical and Mathematical Physics, Harvard University2009–2013

Publications (34)

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
arXiv.org · 2024
3,137
cited
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
On the Theory of Transfer Learning: The Importance of Task Diversity
Neural Information Processing Systems · 2020
242
cited
Provable Meta-Learning of Linear Representations
International Conference on Machine Learning · 2020
211
cited
Stochastic Cubic Regularization for Fast Nonconvex Optimization
Neural Information Processing Systems · 2017
180
cited
Averaging Stochastic Gradient Descent on Riemannian Manifolds
Annual Conference Computational Learning Theory · 2018
109
cited
Bulk viscosity and cavitation in boost-invariant hydrodynamic expansion
2009
73
cited
Pretraining Data Mixtures Enable Narrow Model Selection Capabilities in Transformer Models
arXiv.org · 2023
51
cited
Quantitative criticism of literary relationships
Proceedings of the National Academy of Sciences of the United States of America · 2017
49
cited
Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
arXiv.org · 2024
46
cited
Overparameterization Improves Robustness to Covariate Shift in High Dimensions
Neural Information Processing Systems · 2021
45
cited
Algorithms for heavy-tailed statistics: regression, covariance estimation, and beyond
Symposium on the Theory of Computing · 2019
39
cited
Magnetic Hamiltonian Monte Carlo
International Conference on Machine Learning · 2016
38
cited
Optimal Robust Linear Regression in Nearly Linear Time
arXiv.org · 2020
38
cited
Rao-Blackwellized Stochastic Gradients for Discrete Distributions
International Conference on Machine Learning · 2018
34
cited
Evaluating Stream Filtering for Entity Profile Updates for TREC 2013
Text Retrieval Conference · 2013
32
cited
Lost Relatives of the Gumbel Trick
International Conference on Machine Learning · 2017
28
cited
Covariate Shift in High-Dimensional Random Feature Regression
arXiv.org · 2021
25
cited
Optimal Mean Estimation without a Variance
Annual Conference Computational Learning Theory · 2020
24
cited
Particle Gibbs for Infinite Hidden Markov Models
Neural Information Processing Systems · 2015
22
cited
Sotabase
Nilesh Tripuraneni | Researcher Profile | Sotabase | Sotabase