Bin Gu

23

Papers

44

Total Citations

Papers (23)

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption

Federated Causal Discovery from Heterogeneous Data

Dynamic Spiking Graph Neural Networks

Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent

Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging

NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks

Double Momentum Method for Lower-Level Constrained Bilevel Optimization

Query Efficient Black-Box Visual Prompting with Subspace Learning

Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models

Leveraging First and Zeroth-Order Gradient to Address Imbalanced Black-Box Prompt Tuning via Minimax Optimization

Enhancing Training of Spiking Neural Network with Stochastic Latency

Iterative Regularization with K-support Norm: An Important Complement to Sparse Recovery

Training Neural Networks Using Features Replay

Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity

GAGA: Deciphering Age-path of Generalized Self-paced Regularizer

Zeroth-Order Negative Curvature Finding: Escaping Saddle Points without Gradients

A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning

Direct Training of SNN using Local Zeroth Order Method

Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism

Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization

A New Generalized Error Path Algorithm for Model Selection

Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines

Decoupled Parallel Backpropagation with Convergence Guarantee