5 papers
Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search
Jello Zhou, Vudtiwat Ngampruetikorn, David J. Schwab
Stochastic resetting -- intermittently returning a process to a fixed reference state -- has emerged as an effective mechanism for optimizing first-passage properties. Existing the…
Understanding temperature tuning in energy-based models
Peter W Fields, Vudtiwat Ngampruetikorn, David J Schwab +1
Generative models of complex systems often require post-hoc parameter adjustments to produce useful outputs. For example, energy-based models for protein design are sampled at an a…
Data coarse graining can improve model performance
Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
Lossy data transformations by definition lose information. Yet, in modern machine learning, methods like data pruning and lossy data augmentation can help improve generalization pe…
When can in-context learning generalize out of task distribution?
Chase Goddard, Lindsay M. Smith, Vudtiwat Ngampruetikorn +1
In-context learning (ICL) is a remarkable capability of pretrained transformers that allows models to generalize to unseen tasks after seeing only a few examples. We investigate em…
Generalization vs. Specialization under Concept Shift
Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
Machine learning models are often brittle under distribution shift, i.e., when data distributions at test time differ from those during training. Understanding this failure mode is…