Energy-based Preference Optimization for Test-time Adaptation

Test-Time Adaptation (TTA) enhances model robustness by enabling adaptation to target distributions that differ from training distributions, improving real-world generalizability. Existing TTA approaches focus on adjusting the conditional distribution; however these methods often depend on uncertain predictions in the absence of label information, leading to unreliable performance. Energy-based frameworks suggest a promising alternative to address distribution shifts without relying on uncertain predictions, instead computing the marginal distribution of target data. However, they involve the critical challenge of requiring extensive SGLD sampling, which is impractical for test-time scenarios requiring immediate adaptation. In this work, we propose Energy-based Preference Optimization for Test-time Adaptation (EPOTTA), which is based on a sampling free strategy. We first parameterize the target model using a pretrained model and residual energy function, enabling marginal likelihood maximization of target data without sampling. Building on the observation that the parameterization is mathematically equivalent to DPO objective, we then directly adapt the model to a target distribution without explicitly training the residual. Our experiments verify that EPOTTA is well-calibrated and performant while achieving computational efficiency.

@article{han2025_2505.19607,
  title={ Energy-based Preference Optimization for Test-time Adaptation },
  author={ Yewon Han and Seoyun Yang and Taesup Kim },
  journal={arXiv preprint arXiv:2505.19607},
  year={ 2025 }
}