Aaron Mishkin

19 papers A* 6A 1Journal 12
YearRankTypeTitle / Venue / Authors
2025 A* conf
Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality.
ICLR
Sungyoon Kim, Aaron Mishkin, Mert Pilanci
2025 J jnl
Glocal Smoothness: Line Search can really help!
CoRR
Curtis Fox, Aaron Mishkin, Sharan Vaswani, Mark Schmidt
2025 A conf
Level Set Teleportation: An Optimization Perspective.
AISTATS
Aaron Mishkin, Alberto Bietti, Robert M. Gower
2024 J jnl
A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features.
CoRR
Emi Zeger, Yifei Wang, Aaron Mishkin, Tolga Ergen, Emmanuel J. Candès, Mert Pilanci
2024 A* conf
Directional Smoothness and Gradient Methods: Convergence and Adaptivity.
NeurIPS
Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, Robert M. Gower
2024 J jnl
Directional Smoothness and Gradient Methods: Convergence and Adaptivity.
CoRR
Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, Robert M. Gower
2024 J jnl
Exploring the loss landscape of regularized neural networks via convex duality.
CoRR
Sungyoon Kim, Aaron Mishkin, Mert Pilanci
2024 J jnl
Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation.
CoRR
Aaron Mishkin, Mert Pilanci, Mark Schmidt
2024 J jnl
Level Set Teleportation: An Optimization Perspective.
CoRR
Aaron Mishkin, Alberto Bietti, Robert M. Gower
2023 J jnl
Analyzing and Improving Greedy 2-Coordinate Updates for Equality-Constrained Optimization via Steepest Descent in the 1-Norm.
CoRR
Amrutha Varshini Ramesh, Aaron Mishkin, Mark Schmidt, Yihan Zhou, Jonathan Wilder Lavington, Jennifer She
2023 A* conf
Optimal Sets and Solution Paths of ReLU Networks.
ICML
Aaron Mishkin, Mert Pilanci
2023 J jnl
Optimal Sets and Solution Paths of ReLU Networks.
CoRR
Aaron Mishkin, Mert Pilanci
2022 A* conf
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions.
ICML
Aaron Mishkin, Arda Sahiner, Mert Pilanci
2022 J jnl
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions.
CoRR
Aaron Mishkin, Arda Sahiner, Mert Pilanci
2020 J jnl
To Each Optimizer a Norm, To Each Norm its Generalization.
CoRR
Sharan Vaswani, Reza Babanezhad, Jose Gallego, Aaron Mishkin, Simon Lacoste-Julien, Nicolas Le Roux
2019 A* conf
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates.
NeurIPS
Sharan Vaswani, Aaron Mishkin, Issam H. Laradji, Mark Schmidt, Gauthier Gidel, Simon Lacoste-Julien
2019 J jnl
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates.
CoRR
Sharan Vaswani, Aaron Mishkin, Issam H. Laradji, Mark Schmidt, Gauthier Gidel, Simon Lacoste-Julien
2018 A* conf
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient.
NeurIPS
Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan
2018 J jnl
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient.
CoRR
Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, Mark Schmidt, Mohammad Emtiyaz Khan