{"ID":2856150,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.11068","arxiv_id":"2510.11068","title":"Efficient Test-Time Adaptation through Latent Subspace Coefficients Search","abstract":"Real-world deployment often exposes models to distribution shifts, making test-time adaptation (TTA) critical for robustness. Yet most TTA methods are unfriendly to edge deployment, as they rely on backpropagation, activation buffering, or test-time mini-batches, leading to high latency and memory overhead. We propose \\textbf{ELaTTA} (\\textit{Efficient Latent Test-Time Adaptation}), a gradient-free framework for single-instance TTA under strict on-device constraints. ELaTTA freezes model weights and adapts each test sample by optimizing a low-dimensional coefficient vector in a source-induced principal latent subspace, pre-computed offline via truncated SVD and stored with negligible overhead. At inference, ELaTTA encourages prediction confidence by optimizing the $k$-D coefficients with CMA-ES, effectively optimizing a Gaussian-smoothed objective and improving stability near decision boundaries. Across six benchmarks and multiple architectures, ELaTTA achieves state-of-the-art accuracy under both strict and continual single-instance protocols, while reducing compute by up to \\emph{63$\\times$} and peak memory by up to \\emph{11$\\times$}. We further demonstrate on-device deployment on a ZYNQ-7020 platform.","short_abstract":"Real-world deployment often exposes models to distribution shifts, making test-time adaptation (TTA) critical for robustness. Yet most TTA methods are unfriendly to edge deployment, as they rely on backpropagation, activation buffering, or test-time mini-batches, leading to high latency and memory overhead. We propose...","url_abs":"https://arxiv.org/abs/2510.11068","url_pdf":"https://arxiv.org/pdf/2510.11068v3","authors":"[\"Xinyu Luo\",\"Jie Liu\",\"Kecheng Chen\",\"Junyi Yang\",\"Bo Ding\",\"Arindam Basu\",\"Haoliang Li\"]","published":"2025-10-13T07:08:52Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"eess.AS\",\"eess.IV\"]","methods":"[]","has_code":false}