Hugo Cui
11 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🗺️ Taxonomy Completionist (14) 🌍 Conference Polyglot (4) 🐝 Cross-Pollinator (12) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer
🏆
Keyword Champion
(2)
👑
Triple Crown
💎
Century Club
(11)
Conferences
ICML (5)
NIPS (4)
AISTATS (1)
ICLR (1)
Top co-authors
Keywords
deep neural network
(2)
ridge regression
(2)
random feature model
(2)
generalization error
(2)
kernel regression
(2)
mean squared error
(1)
phase transition
(1)
denoising autoencoder
(1)
feature map
(1)
implicit regularization
(1)
learning curve
(1)
test error
(1)
skip connection
(1)
mean-squared error
(1)
gaussian mixture
(1)
teacher-student model
(1)
high-dimensional asymptotics
(1)
bayes-optimal error
(1)
extensive-width limit
(1)
gaussian universality
(1)
Papers
A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
AISTATS 2025
Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
ICML 2025
Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
ICLR 2024
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
NIPS 2024
Asymptotics of feature learning in two-layer networks after one gradient-step
ICML 2024
Asymptotics of Learning with Deep Structured (Random) Features
ICML 2024
Bayes-optimal Learning of Deep Random Networks of Extensive-width
ICML 2023
Deterministic equivalent and error universality of deep random features learning
ICML 2023
High-dimensional Asymptotics of Denoising Autoencoders
NIPS 2023
Learning curves of generic features maps for realistic datasets with a teacher-student model
NIPS 2021
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime
NIPS 2021