Sotabase

Career

· Assistant Professor in Electrical Engineering, Stanford University2018–
· Assistant Professor of Electrical Engineering and Computer Science, University of Michigan2017–
· Postdoctoral Researcher, Department of Mathematics, Stanford University2016–
· Ph.D. student in Electrical Engineering and Computer Science, UC Berkeley2010–

Publications (178)

Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence
SIAM Journal on Optimization · 2015
287
cited
Iterative Hessian Sketch: Fast and Accurate Solution Approximation for Constrained Least-Squares
Journal of machine learning research · 2014
214
cited
Randomized sketches of convex programs with sharp guarantees
2014 IEEE International Symposium on Information Theory · 2014
186
cited
Randomized sketches for kernels: Fast and optimal non-parametric regression
arXiv.org · 2015
184
cited
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-Layer Networks
International Conference on Machine Learning · 2020
133
cited
Sparse learning via Boolean relaxations
Mathematical programming · 2015
77
cited
Revealing the Structure of Deep Neural Networks via Convex Duality
International Conference on Machine Learning · 2020
75
cited
Convex Geometry and Duality of Over-parameterized Neural Networks
Journal of machine learning research · 2020
63
cited
Recovery of Sparse Probability Measures via Convex Programming
Neural Information Processing Systems · 2012
55
cited
Compressing Large Language Models using Low Rank and Low Precision Decomposition
Neural Information Processing Systems · 2024
46
cited
Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time
International Conference on Learning Representations · 2020
46
cited
Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms
International Conference on Learning Representations · 2020
45
cited
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers
International Conference on Machine Learning · 2022
35
cited
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs
International Conference on Machine Learning · 2021
34
cited
Matrix Compression via Randomized Low Rank and Low Precision Factorization
Neural Information Processing Systems · 2023
34
cited
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
International Conference on Machine Learning · 2024
34
cited
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization
International Conference on Learning Representations · 2021
33
cited
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
International Conference on Machine Learning · 2022
33
cited
Convex Geometry of Two-Layer ReLU Networks: Implicit Autoencoding and Interpretable Models
International Conference on Artificial Intelligence and Statistics · 2020
32
cited
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update
Neural Information Processing Systems · 2021
31
cited
Sotabase
Mert Pilanci | Researcher Profile | Sotabase | Sotabase