Theodor Misiakiewicz
12 papers · 2017–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π Conference Polyglot (2) π Academic Marathon (8) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Interdisciplinary Bridge
π
Academic Marathon
(8)
π
Keyword Champion
π
Trend Setter
π
Century Club
(12)
π₯
Unstoppable
(7)
β
The Questioner
Conferences
COLT (6)
NIPS (6)
Top co-authors
Keywords
stochastic gradient descent
(5)
neural network
(4)
generalization error
(3)
kernel methods
(3)
learning theory
(2)
neural tangent kernel
(2)
random feature
(2)
kernel ridge regression
(2)
sparse function
(2)
semidefinite programming
(1)
reproducing kernel hilbert space
(1)
probability distribution
(1)
linear methods
(1)
invariance learning
(1)
feature learning
(1)
image classification
(1)
asymptotic analysis
(1)
eigenvalue decay
(1)
sample complexity
(1)
query complexity
(1)
Papers
A Theory of Learning with Autoregressive Chain of Thought
COLT 2025
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
NIPS 2024
Dimension-free deterministic equivalents and scaling laws for random feature regression
NIPS 2024
SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics
COLT 2023
The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
COLT 2022
Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression
NIPS 2022
Learning with convolution and pooling operations in kernel methods
NIPS 2022
Learning with invariances in random features and kernel models
COLT 2021
When Do Neural Networks Outperform Kernel Methods?
NIPS 2020
Limitations of Lazy Training of Two-layers Neural Network
NIPS 2019
Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit
COLT 2019
Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality
COLT 2017