activity
20242026
collaborators

5 papers

cs.LG2026

Deriving Hyperparameter Scaling Laws via Modern Optimization Theory

Egor Shulgin, Dimitri von Rütte, Tianyue H. Zhang +3

Hyperparameter transfer has become an important component of modern large-scale training recipes. Existing methods, such as muP, primarily focus on transfer between model sizes, wi…

cs.LG2025

Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret

Bingshan Hu, Zhiming Huang, Tianyue H. Zhang +2

We address differentially private stochastic bandit problems from the angles of exploring the deep connections among Thompson Sampling with Gaussian priors, Gaussian mechanisms, an…

cs.LG2024

Understanding Adam Requires Better Rotation Dependent Assumptions

Tianyue H. Zhang, Lucas Maes, Alan Milligan +5

Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This paper investigates Adam's sensitivity t…

cs.LG2024

On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization

Motahareh Sohrabi, Juan Ramirez, Tianyue H. Zhang +2

Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problems are solved via their min-max Lagrangia…

cs.LG2024

Efficient and Adaptive Posterior Sampling Algorithms for Bandits

Bingshan Hu, Zhiming Huang, Tianyue H. Zhang +2

We study Thompson Sampling-based algorithms for stochastic bandits with bounded rewards. As the existing problem-dependent regret bound for Thompson Sampling with Gaussian priors […