Sebastian Goldt
15 papers · 2019–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
๐ Interdisciplinary Bridge ๐ฃ Hot Topic Early Bird ๐งญ Keyword Pioneer ๐ Conference Polyglot (3) ๐ Academic Marathon (6)
๐
Cross-Pollinator
(13)
๐บ๏ธ
Taxonomy Completionist
(29)
๐
Keyword Champion
(2)
๐
Century Club
(15)
๐๏ธ
Keyword Collector
(59)
๐ฅ
Unstoppable
(5)
Conferences
ICML (8)
NIPS (6)
UAI (1)
Top co-authors
Keywords
neural network
(6)
stochastic gradient descent
(3)
simplicity bia
(2)
neural network optimization
(2)
catastrophic forgetting
(2)
generalization error
(2)
teacher-student model
(2)
task similarity
(2)
continual learning
(2)
teacher-student setup
(2)
feature learning
(2)
representation learning
(2)
adversarial machine learning
(1)
knowledge transfer
(1)
self-supervised learning
(1)
natural language processing
(1)
transfer learning
(1)
computational complexity
(1)
online learning
(1)
network pruning
(1)
Papers
Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
ICML 2025
Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks
ICML 2024
Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
NIPS 2024
A distributional simplicity bias in the learning dynamics of transformers
NIPS 2024
Attacks on Online Learners: a Teacher-Student Analysis
NIPS 2023
Quantifying lottery tickets under label noise: accuracy, calibration, and complexity
UAI 2023
Neural networks trained with SGD learn distributions of increasing complexity
ICML 2023
Maslowโs Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation
ICML 2022
Redundant representations help generalization in wide neural networks
NIPS 2022
The dynamics of representation learning in shallow, non-linear autoencoders
ICML 2022
Align, then memorise: the dynamics of learning with feedback alignment
ICML 2021
Learning curves of generic features maps for realistic datasets with a teacher-student model
NIPS 2021
Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
ICML 2021
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
ICML 2021
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
NIPS 2019