Energy-based Preference Optimization for Test-time Adaptation

• URL: http://arxiv.org/abs/2505.19607v1
• Date: Mon, 26 May 2025 07:21:32 GMT
• Title: Energy-based Preference Optimization for Test-time Adaptation
• Authors: Yewon Han, Seoyun Yang, Taesup Kim,
• Abstract summary: Test-Time Adaptation (TTA) approaches focus on adjusting the conditional distribution.<n>These methods often depend on uncertain predictions in the absence of label information, leading to unreliable performance.<n>Energy-based frameworks suggest a promising alternative to address distribution shifts without relying on uncertain predictions, instead computing the marginal distribution of target data.
• Score: 4.379304291229695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks [1.4671424999873808]
  Uncertainty is critical in safety-sensitive applications but is often omitted from off-the-shelf neural networks due to adverse effects on predictive performance.<n>We propose a theoretically grounded framework for post-hoc uncertainty estimation in regression tasks by fitting an auxiliary model to both original inputs and frozen model outputs.
  arXiv  Detail & Related papers  (2025-06-01T09:13:27Z)
• COME: Test-time adaption by Conservatively Minimizing Entropy [45.689829178140634]
  Conservatively Minimize the Entropy (COME) is a drop-in replacement of traditional entropy (EM) COME explicitly models the uncertainty by characterizing a Dirichlet prior distribution over model predictions. We show that COME achieves state-of-the-art performance on commonly used benchmarks.
  arXiv  Detail & Related papers  (2024-10-12T09:20:06Z)
• Leveraging free energy in pretraining model selection for improved fine-tuning [4.005483185111992]
  We introduce a free energy criterion that quantifies a checkpoint's adaptability by measuring the concentration of nearby favorable parameters for the downstream task. We provide empirical evidence that the free energy criterion reliably correlates with improved fine-tuning performance.
  arXiv  Detail & Related papers  (2024-10-08T01:50:21Z)
• Test-Time Model Adaptation with Only Forward Passes [68.11784295706995]
  Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. We propose a test-time Forward-Optimization Adaptation (FOA) method. FOA runs on quantized 8-bit ViT, outperforms gradient-based TENT on full-precision 32-bit ViT, and achieves an up to 24-fold memory reduction on ImageNet-C.
  arXiv  Detail & Related papers  (2024-04-02T05:34:33Z)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [55.17761802332469]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample. Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications. We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction [27.434939269672288]
  We use PAC-Bayes theory to obtain generalization bounds on the coverage and the efficiency of set-valued predictors. We leverage these theoretical results to provide a practical algorithm for using calibration data to fine-tune the parameters of a model and score function. We evaluate the approach on regression and classification tasks, and outperform baselines calibrated using a Hoeffding bound-based PAC guarantee on ICP.
  arXiv  Detail & Related papers  (2023-12-07T19:40:44Z)
• Energy-Based Test Sample Adaptation for Domain Generalization [81.04943285281072]
  We propose energy-based sample adaptation at test time for domain. To adapt target samples to source distributions, we iteratively update the samples by energy minimization. Experiments on six benchmarks for classification of images and microblog threads demonstrate the effectiveness of our proposal.
  arXiv  Detail & Related papers  (2023-02-22T08:55:09Z)
• Uncertainty-guided Source-free Domain Adaptation [77.3844160723014]
  Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. We propose quantifying the uncertainty in the source model predictions and utilizing it to guide the target adaptation.
  arXiv  Detail & Related papers  (2022-08-16T08:03:30Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Adaptive Sequential Design for a Single Time-Series [2.578242050187029]
  We learn an optimal, unknown choice of the controlled components of a design in order to optimize the expected outcome. We adapt the randomization mechanism for future time-point experiments based on the data collected on the individual over time.
  arXiv  Detail & Related papers  (2021-01-29T22:51:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.