4 papers
When Context Changes: Understanding Update Failures in LLMs
Junyu Guo, Yuchen Fang, Shangding Gu +3
As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old value of the same variable,…
A Trust-Region Interior-Point Stochastic Sequential Quadratic Programming Method
Yuchen Fang, Jihun Kim, Sen Na +2
In this paper, we propose a trust-region interior-point stochastic sequential quadratic programming (TR-IP-SSQP) method for solving optimization problems with a stochastic objectiv…
Why is Normalization Preferred? A Worst-Case Complexity Theory for Stochastically Preconditioned SGD under Heavy-Tailed Noise
Yuchen Fang, James Demmel, Javad Lavaei
We develop a worst-case complexity theory for stochastically preconditioned stochastic gradient descent (SPSGD) and its accelerated variants under heavy-tailed noise, a setting tha…
3DGS-TR: Scalable Second-Order Trust-Region Method for 3D Gaussian Splatting
Roger Hsiao, Yuchen Fang, Xiangru Huang +6
We propose 3DGS-TR,a second-order optimizer for accelerating the scene training problem in 3D Gaussian Splatting (3DGS). Unlike existing second-order approaches that rely on ex…