Figure 1: Evaluation of T abEBM and other state-of-the-art tabular generative methods across six key metrics (larger area indicates better performance).

This leads to a new MU paradigm, termed prune first, then unlearn, which infuses a sparse model prior into the unlearning process.

Different distribution shifts require different algorithmic and operational interventions. Methodological research must be grounded by the specific shifts they address.

A central notion in practical and theoretical machine learning is that of a weak learner, classifiers that achieve better-than-random performance (on any given distribution over data), even by a small margin. Such weak learners form the practical basis for canonical machine learning methods such as boosting.

We consider the problem of extracting a reward function by comparing a decision-making diffusion model that models low-reward behavior and one that models high-reward behavior; a setting related to inverse reinforcement learning. We first define the notion of a relative reward function of two diffusion models and show conditions under which it exists and is unique.