Picture for Yu-Xiang Wang

Yu-Xiang Wang

University of California Santa Barbara

Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach

Add code
Apr 09, 2025
Viaarxiv icon

Purifying Approximate Differential Privacy with Randomized Post-processing

Add code
Mar 27, 2025
Viaarxiv icon

Dynamic Pricing with Adversarially-Censored Demands

Add code
Feb 10, 2025
Figure 1 for Dynamic Pricing with Adversarially-Censored Demands
Viaarxiv icon

A Proximal Operator for Inducing 2:4-Sparsity

Add code
Jan 29, 2025
Figure 1 for A Proximal Operator for Inducing 2:4-Sparsity
Figure 2 for A Proximal Operator for Inducing 2:4-Sparsity
Figure 3 for A Proximal Operator for Inducing 2:4-Sparsity
Figure 4 for A Proximal Operator for Inducing 2:4-Sparsity
Viaarxiv icon

Joint Pricing and Resource Allocation: An Optimal Online-Learning Approach

Add code
Jan 29, 2025
Viaarxiv icon

No-Regret Linear Bandits under Gap-Adjusted Misspecification

Add code
Jan 09, 2025
Viaarxiv icon

On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures

Add code
Jan 03, 2025
Viaarxiv icon

SoK: Watermarking for AI-Generated Content

Add code
Nov 27, 2024
Viaarxiv icon

NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation

Add code
Oct 30, 2024
Figure 1 for NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
Figure 2 for NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
Figure 3 for NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
Figure 4 for NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
Viaarxiv icon

Efficiently Identifying Watermarked Segments in Mixed-Source Texts

Add code
Oct 04, 2024
Viaarxiv icon