Aaron Mishkin

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 14

Top Topics

Natural Gradient

Faster Convergence

Top Venues

Publications

Aaron Mishkin, Alberto Bietti, Robert M. Gower
Level Set Teleportation: An Optimization Perspective. CoRR (2024)
Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, Robert M. Gower
Directional Smoothness and Gradient Methods: Convergence and Adaptivity. CoRR (2024)
Aaron Mishkin, Mert Pilanci, Mark Schmidt
Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation. CoRR (2024)
Emi Zeger, Yifei Wang, Aaron Mishkin, Tolga Ergen, Emmanuel J. Candès, Mert Pilanci
A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features. CoRR (2024)
Aaron Mishkin, Mert Pilanci
Optimal Sets and Solution Paths of ReLU Networks. CoRR (2023)
Amrutha Varshini Ramesh, Aaron Mishkin, Mark Schmidt, Yihan Zhou, Jonathan Wilder Lavington, Jennifer She
Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm. CoRR (2023)
Aaron Mishkin, Mert Pilanci
Optimal Sets and Solution Paths of ReLU Networks. ICML (2023)
Aaron Mishkin, Arda Sahiner, Mert Pilanci
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions. ICML (2022)
Aaron Mishkin, Arda Sahiner, Mert Pilanci
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions. CoRR (2022)
Sharan Vaswani, Reza Babanezhad, Jose Gallego, Aaron Mishkin, Simon Lacoste-Julien, Nicolas Le Roux
To Each Optimizer a Norm, To Each Norm its Generalization. CoRR (2020)
Sharan Vaswani, Aaron Mishkin, Issam H. Laradji, Mark Schmidt, Gauthier Gidel, Simon Lacoste-Julien
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates. NeurIPS (2019)
Sharan Vaswani, Aaron Mishkin, Issam H. Laradji, Mark Schmidt, Gauthier Gidel, Simon Lacoste-Julien
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates. CoRR (2019)
Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient. NeurIPS (2018)
Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient. CoRR (2018)