3 papers
cs.LG2026
Intentional Updates for Streaming Reinforcement Learning
Arsalan Sharifnassab, Mohamed Elsayed, Kris De Asis +2
In gradient-based learning, a step size chosen in parameter units does not produce a predictable per-step change in function output. This often leads to instability in the streamin…
cs.LG2025
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters
Arsalan Sharifnassab, Saber Salehkaleybar, Richard Sutton
We address the challenge of optimizing meta-parameters (hyperparameters) in machine learning, a key factor for efficient training and high model performance. Rather than relying on…
cs.LG2024
Soft Preference Optimization: Aligning Language Models to Expert Distributions
Arsalan Sharifnassab, Saber Salehkaleybar, Sina Ghiassian +2
We propose Soft Preference Optimization (SPO), a method for aligning generative models, such as Large Language Models (LLMs), with human preferences, without the need for a reward…