Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models

• URL: http://arxiv.org/abs/2606.14222v1
• Date: Fri, 12 Jun 2026 08:02:03 GMT
• Title: Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Models
• Abstract summary: Time Series Foundation Models (TSFMs) have advanced zero-shot forecasting across diverse domains.<n>Many existing online adaptation methods still rely on white-box access for parameter fine-tuning or gradient backpropagation.<n>In black-box online adaptation for TSFMs, what should we learn?<n>We answer this with an insight: the predictive errors of the base model are conditioned on both the input and output of the base model.
• Score: 14.827848278985101
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid evolution of Time Series Foundation Models (TSFMs) has advanced zero-shot forecasting across diverse domains. Inspired by the current form of Large Language Models, future TSFMs may be offered as commercialized, closed-source API services. However, many existing online adaptation methods still rely on white-box access for parameter fine-tuning or gradient backpropagation. This paradigm mismatch raises a question: In black-box online adaptation for TSFMs, what should we learn? We answer this with an insight: the predictive errors of the base model are conditioned on both the input and output of the base model (i.e., the context of errors). To validate this insight, we propose ORCA (Online Residual Contextual Adaptation). We conduct extensive experiments across 5 state-of-the-art TSFMs and 8 datasets to demonstrate the effectiveness of our approach. Furthermore, through ablation studies, we quantitatively analyze the impact of different adapter learning hypotheses on the final adaptation performance in black-box online adaptation. Code available at https://github.com/Fifthky/ORCA.

Related papers

• Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning [49.3087425299849]
  World models let agents plan by predicting the consequences of their actions, but changes in the environment can make them inaccurate.<n>Existing approaches trade off computational cost against expressivity, i.e., the range of models a method can produce.<n>We present CLAW, which addresses this tradeoff by using a hypernetwork to generate adapters at test time.
  arXiv  Detail & Related papers  (2026-09-10T23:16:40Z)
• Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learning [47.975618905252354]
  Multimodal 3D vision-language models show strong generalization across diverse 3D tasks, but their performance still degrades notably under domain shifts.<n>This has motivated recent studies on test-time adaptation, which enables models to adapt online using test-time data.<n>We propose BayesMM, a Multimodal Distribution Learning framework for test-time point cloud analysis.
  arXiv  Detail & Related papers  (2026-03-23T15:03:47Z)
• Online time series prediction using feature adjustment [3.07487290622028]
  Time series forecasting is of significant importance across various domains.<n>Time series online learning methods focus on two main aspects: selecting suitable parameters to update.<n>We propose that distribution shifts stem from changes in underlying latent factors influencing the data.
  arXiv  Detail & Related papers  (2025-09-04T01:54:48Z)
• Adaptation Odyssey in LLMs: Why Does Additional Pretraining Sometimes Fail to Improve? [19.34040322172224]
  We show that training a model on a text domain could degrade its perplexity on the test portion of the same domain. Our findings will guide us in determining when to adapt a model vs when to rely on its foundational capabilities.
  arXiv  Detail & Related papers  (2024-10-08T00:37:16Z)
• Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review [50.78587571704713]
  Learn-Focus-Review (LFR) is a dynamic training approach that adapts to the model's learning progress.<n>LFR tracks the model's learning performance across data blocks (sequences of tokens) and prioritizes revisiting challenging regions of the dataset.<n>Compared to baseline models trained on the full datasets, LFR consistently achieved lower perplexity and higher accuracy.
  arXiv  Detail & Related papers  (2024-09-10T00:59:18Z)
• 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)
• Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation [71.21346469382821]
  We introduce collaborative black-box tuning (CBBT) for both textual prompt optimization and output feature adaptation for black-box models. CBBT is extensively evaluated on eleven downstream benchmarks and achieves remarkable improvements compared to existing black-box VL adaptation methods.
  arXiv  Detail & Related papers  (2023-12-26T06:31:28Z)
• Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback [97.0874638345205]
  generative models can be great test-time adapters for discriminative models. Our method, Diffusion-TTA, adapts pre-trained discriminative models to each unlabelled example in the test set. We show Diffusion-TTA significantly enhances the accuracy of various large-scale pre-trained discriminative models.
  arXiv  Detail & Related papers  (2023-11-27T18:59:53Z)

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.