Berfin Simsek
8 papers · 2020–2025 · 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
(17)
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(8)
Deep Learning
(6)
Architectures
(5)
Optimization & Theory · Machine Learning
(5)
Core Methods
(3)
Optimization & Theory · Deep Learning
(2)
Artificial Intelligence
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Application Areas
(1)
Core AI
(1)
Learning Types
(1)
Mathematics
(1)
Resources & Methods
(1)
Keywords
neural network
(2)
kernel ridge regression
(2)
loss landscape
(2)
gradient flow
(2)
gradient descent
(1)
generalization error
(1)
identifiability
(1)
associative memory
(1)
random matrix theory
(1)
relu activation
(1)
stationary point
(1)
implicit regularization
(1)
fixed point
(1)
weight averaging
(1)
saddle point
(1)
affine subspace
(1)
random feature model
(1)
critical point
(1)
overparameterized neural network
(1)
network embedding
(1)
Papers
Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence
AISTATS 2025
Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding
ICLR 2025
Expand-and-Cluster: Parameter Recovery of Neural Networks
ICML 2024
Learning Associative Memories with Gradient Descent
ICML 2024
Should Under-parameterized Student Networks Copy or Average Teacher Weights?
NeurIPS 2023
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
ICML 2021
Implicit Regularization of Random Feature Models
ICML 2020
Kernel Alignment Risk Estimator: Risk Prediction from Training Data
NeurIPS 2020