Aaron Mishkin
7 papers · 2018–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
convex optimization
(3)
convergence rate
(3)
global optimum
(2)
gradient descent
(2)
relu network
(2)
loss landscape
(1)
natural gradient
(1)
step size adaptation
(1)
regularization path
(1)
solution path
(1)
proximal gradient
(1)
stationary point
(1)
uncertainty estimation
(1)
bayesian deep learning
(1)
convex duality
(1)
critical point
(1)
two-layer neural network
(1)
convex program
(1)
line search
(1)
hessian-vector product
(1)
Papers
Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality
ICLR 2025
Level Set Teleportation: An Optimization Perspective
AISTATS 2025
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
NeurIPS 2024
Optimal Sets and Solution Paths of ReLU Networks
ICML 2023
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions
ICML 2022
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
NeurIPS 2019
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
NeurIPS 2018