Tian Ding
6 papers · 2024–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
ICLR (2)
NIPS (2)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
stochastic gradient descent
(1)
black-box optimization
(1)
neural network optimization
(1)
continuous optimization
(1)
neural network theory
(1)
gradient descent
(1)
linear programming
(1)
learning rate
(1)
optimization algorithm
(1)
adam optimizer
(1)
zeroth-order optimization
(1)
gradient approximation
(1)
prompt optimization
(1)
prompt tuning
(1)
finite difference method
(1)
large language model
(1)
graph neural network
(1)
hessian spectrum
(1)
black-box tuning
(1)
polylogarithmic depth
(1)
Papers
Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming
ICLR 2025
Adam-mini: Use Fewer Learning Rates To Gain More
ICLR 2025
On the Power of Small-size Graph Neural Networks for Linear Programming
NIPS 2024
Why Transformers Need Adam: A Hessian Perspective
NIPS 2024
Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization
EMNLP 2024
PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming
ICML 2024