Ruoyu Sun

20

Papers

2

Total Citations

Papers (20)

When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach

Towards Explaining the Power of Constant-depth Graph Neural Networks for Structured Linear Programming

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

How Graph Neural Networks Learn: Lessons from Training Dynamics

PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming

Max-Sliced Wasserstein Distance and Its Use for GANs

Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning

Improved Iteration Complexity Bounds of Cyclic Block Coordinate Descent for Convex Problems

Adding One Neuron Can Eliminate All Bad Local Minima

A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems

Towards a Better Global Loss Landscape of GANs

Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data

When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work

Stability Analysis and Generalization Bounds of Adversarial Training

Does Momentum Change the Implicit Regularization on Separable Data?

Adam Can Converge Without Any Modification On Update Rules

DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data

Balanced Training for Sparse GANs

PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

Understanding the Loss Surface of Neural Networks for Binary Classification