Andi Han
18 papers · 2021–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (12)
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(6)
🏆
Grand Slam
🌱
Topic Pioneer
💎
Century Club
(17)
⚡
Prolific Year
(5)
❓
The Questioner
Conferences
ICML (5)
NIPS (5)
ICLR (4)
AAAI (1)
ACML (1)
AISTATS (1)
IJCAI (1)
Top co-authors
Keywords
riemannian optimization
(3)
attention mechanism
(2)
convergence acceleration
(1)
stochastic gradient
(1)
representation learning
(1)
stochastic gradient descent
(1)
sparse coding
(1)
gradient descent
(1)
riemannian manifold
(1)
in-context learning
(1)
semantic representation
(1)
sharpness-aware minimization
(1)
neural network optimization
(1)
parameter efficient
(1)
label noise
(1)
non-convex optimization
(1)
signal-to-noise ratio
(1)
weisfeiler-lehman test
(1)
transformer architecture
(1)
stochastic optimization
(1)
Papers
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
AAAI 2026
On the Feature Learning in Diffusion Models
ICLR 2025
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
ICLR 2025
Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
ICLR 2025
When Graph Neural Networks Meet Dynamic Mode Decomposition
ICLR 2025
Provable In-Context Vector Arithmetic via Retrieving Task Concepts
ICML 2025
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
ICML 2025
On the Role of Label Noise in the Feature Learning Process
ICML 2025
Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method
ICML 2025
Riemannian coordinate descent algorithms on matrix manifolds
ICML 2024
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
NIPS 2024
On the Comparison between Multi-modal and Single-modal Contrastive Learning
NIPS 2024
A Framework for Bilevel Optimization on Riemannian Manifolds
NIPS 2024
SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
NIPS 2024
A New Perspective On the Expressive Equivalence Between Graph Convolution and Attention Models
ACML 2023
Riemannian Accelerated Gradient Methods via Extrapolation
AISTATS 2023
Riemannian Stochastic Recursive Momentum Method for non-Convex Optimization
IJCAI 2021
On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
NIPS 2021