Xinshang Wang
9 papers · 2018–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (5) π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (10) π Interdisciplinary Bridge π Academic Marathon (7)
π
Cross-Pollinator
(13)
π
Grand Slam
Conferences
ICLR (3)
ICML (2)
NIPS (2)
AAAI (1)
AISTATS (1)
Top co-authors
Keywords
convergence rate
(2)
stochastic gradient descent
(2)
convex optimization
(1)
universal approximation
(1)
dynamic regret
(1)
branch and bound
(1)
importance sampling
(1)
message passing
(1)
gradient descent
(1)
variance reduction
(1)
primal-dual algorithm
(1)
complexity analysis
(1)
first-order method
(1)
online matching
(1)
online gradient descent
(1)
heterogeneous sampling
(1)
finite-sum objective
(1)
stochastic variance reduced gradient
(1)
finite-time convergence
(1)
graph neural network
(1)
Papers
Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
ICML 2025
DOCS: Quantifying Weight Similarity for Deeper Insights into Large Language Models
ICLR 2025
Efficient Algorithms for Sum-Of-Minimum Optimization
ICML 2024
Rethinking the Capacity of Graph Neural Networks for Branching Strategy
NIPS 2024
On Representing Mixed-Integer Linear Programs by Graph Neural Networks
ICLR 2023
HeteRSGD: Tackling Heterogeneous Sampling Costs via Optimal Reweighted Stochastic Gradient Descent
AISTATS 2023
On Representing Linear Programs by Graph Neural Networks
ICLR 2023
A Primal-Dual Online Algorithm for Online Matching Problem in Dynamic Environments
AAAI 2021
The Lingering of Gradients: How to Reuse Gradients Over Time
NIPS 2018