{"slug": "leantta-a-backpropagation-free-and-stateless-approach-to-quantized-test-time-on", "title": "LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices", "summary": "Researchers posted arXiv:2503.15889v2 describing LeanTTA, a backpropagation-free, stateless framework for quantized test-time adaptation on edge devices that updates normalization statistics dynamically instead of relying on large batches or historical data. LeanTTA is the first method to combine partial adaptation with quantized module fusion, and the authors report a 15.7% error reduction over state-of-the-art test-time adaptation methods, peak memory usage of only 11.2MB for ResNet18, and on-device adaptation within an order of magnitude of normal inference speeds across sensor modalities.", "body_md": "arXiv:2503.15889v2 Announce Type: replace-cross \nAbstract: While there are many advantages to deploying machine learning models on edge devices, the resource constraints of mobile platforms, the dynamic nature of the environment, and differences between the distribution of training versus in-the-wild data make such deployments challenging. Current test-time adaptation methods are often memory-intensive and not designed to be quantization-compatible or deployed on low-resource devices. To address these challenges, we present LeanTTA, a novel backpropagation-free and stateless framework for quantized test-time adaptation tailored to edge devices. Our approach minimizes computational costs by dynamically updating normalization statistics without backpropagation, which frees LeanTTA from the common pitfall of relying on large batches and historical data, making our method robust to realistic deployment scenarios. Our approach is the first to enable further computational gains by combining partial adaptation with quantized module fusion. We validate our framework across sensor modalities, demonstrating significant improvements over state-of-the-art TTA methods, including a 15.7% error reduction, peak memory usage of only 11.2MB for ResNet18, and fast adaptation within an order-of-magnitude of normal inference speeds on-device. LeanTTA provides a robust solution for achieving the right trade offs between accuracy and system efficiency in edge deployments, addressing the unique challenges posed by limited data and varied operational conditions.", "url": "https://wpnews.pro/news/leantta-a-backpropagation-free-and-stateless-approach-to-quantized-test-time-on", "canonical_source": "https://www.machinebrief.com/news/leantta-a-backpropagation-free-and-stateless-approach-to-qua-9ttv", "published_at": "2026-10-19 04:00:00+00:00", "updated_at": "2026-10-19 04:50:29.619686+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "ai-infrastructure"], "entities": ["LeanTTA", "arXiv", "ResNet18"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/leantta-a-backpropagation-free-and-stateless-approach-to-quantized-test-time-on", "markdown": "https://wpnews.pro/news/leantta-a-backpropagation-free-and-stateless-approach-to-quantized-test-time-on.md", "text": "https://wpnews.pro/news/leantta-a-backpropagation-free-and-stateless-approach-to-quantized-test-time-on.txt", "jsonld": "https://wpnews.pro/news/leantta-a-backpropagation-free-and-stateless-approach-to-quantized-test-time-on.jsonld"}}