FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation

• URL: http://arxiv.org/abs/2603.04733v1
• Date: Thu, 05 Mar 2026 02:12:48 GMT
• Title: FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation
• Authors: Xingyu Wang, Tao Wang,
• Abstract summary: Test-Time Adaptation is essential for enabling deep learning models to handle real-world data distribution shifts.<n>Backpropagation-based methods are not suitable for low-end deployment devices.<n>We propose Forward-Only Zeroth-Order Optimization (FOZO), a novel and practical backpropagation-free paradigm for TTA.
• Score: 9.28697795097814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-Time Adaptation (TTA) is essential for enabling deep learning models to handle real-world data distribution shifts. However, current approaches face significant limitations: backpropagation-based methods are not suitable for low-end deployment devices, due to their high computation and memory requirements, as well as their tendency to modify model weights during adaptation; while traditional backpropagation-free techniques exhibit constrained adaptation capabilities. In this work, we propose Forward-Only Zeroth-Order Optimization (FOZO), a novel and practical backpropagation-free paradigm for TTA. FOZO leverages a memory-efficient zeroth-order prompt optimization, which is led by objectives optimizing both intermediate feature statistics and prediction entropy. To ensure efficient and stable adaptation over the out-of-distribution data stream, we introduce a dynamically decaying perturbation scale during zeroth-order gradient estimation and theoretically prove its convergence under the TTA data stream assumption. Extensive continual adaptation experiments on ImageNet-C, ImageNet-R, and ImageNet-Sketch demonstrate FOZO's superior performance, achieving 59.52% Top-1 accuracy on ImageNet-C (5K, level 5) and outperforming main gradient-based methods and SOTA forward-only FOA (58.13%). Furthermore, FOZO exhibits strong generalization on quantized (INT8) models. These findings demonstrate that FOZO is a highly competitive solution for TTA deployment in resource-limited scenarios.

Related papers

• Energy-based Preference Optimization for Test-time Adaptation [4.379304291229695]
  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.
  arXiv  Detail & Related papers  (2025-05-26T07:21:32Z)
• DFF: Decision-Focused Fine-tuning for Smarter Predict-then-Optimize with Limited Data [7.70699448711673]
  Decision-focused learning (DFL) offers an end-to-end approach to the predict-then-optimize (PO) framework by training predictive models directly on decision loss (DL)<n>Some predictive models are non-differentiable or black-box, which cannot be adjusted using gradient-based methods.<n>We propose a novel framework, Decision-Focused Fine-tuning (DFF), which embeds the DFL module into the PO pipeline via a novel bias correction module.
  arXiv  Detail & Related papers  (2025-01-03T15:46:25Z)
• 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)
• Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models [68.23649978697027]
  Forecast-PEFT is a fine-tuning strategy that freezes the majority of the model's parameters, focusing adjustments on newly introduced prompts and adapters. Our experiments show that Forecast-PEFT outperforms traditional full fine-tuning methods in motion prediction tasks. Forecast-FT further improves prediction performance, evidencing up to a 9.6% enhancement over conventional baseline methods.
  arXiv  Detail & Related papers  (2024-07-28T19:18:59Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• 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)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation [5.749155230209001]
  Fully-test-time adaptation (F-TTA) can mitigate performance loss due to distribution shifts between train and test data. We present a general framework for improving robustness of F-TTA to noisy samples, inspired by self-paced learning and robust loss functions.
  arXiv  Detail & Related papers  (2023-09-07T18:44:58Z)
• Tent: Fully Test-time Adaptation by Entropy Minimization [77.85911673550851]
  A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions.
  arXiv  Detail & Related papers  (2020-06-18T17:55:28Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.