Search papers, labs, and topics across Lattice.
This paper introduces TRACE-CRC, a novel method for trajectory-aware uncertainty quantification in multi-step channel state information (CSI) prediction, addressing the limitations of existing deep learning approaches that provide only point predictions without calibrated uncertainty. By constructing Frobenius-norm uncertainty balls around predicted CSI matrices and employing a combination of future-step-dependent error profiling and trajectory difficulty stratification, TRACE-CRC ensures that the risk of undercoverage in future frames is minimized. Empirical results demonstrate that TRACE-CRC achieves reliable trajectory-level coverage with significantly smaller uncertainty bounds compared to traditional methods, enhancing the reliability of downstream decisions in wireless communication.
TRACE-CRC reduces uncertainty in multi-step CSI predictions while ensuring robust coverage, outperforming traditional methods with smaller uncertainty bounds.
Reliable prediction of time-varying channel state information (CSI) is essential for efficient wireless communication. Each CSI frame is a matrix-valued representation of the wireless channel response, and a sequence of CSI frames forms a temporal channel trajectory. Modern deep learning-based CSI predictors, however, often provide only point predictions and lack calibrated uncertainty estimates. This limitation is particularly problematic in multi-step CSI prediction, where the target is a sequence of future CSI matrices, and downstream decisions such as beamforming or scheduling may fail if any part of the predicted trajectory is unreliable. We propose trajectory-adaptive calibration and error profiling with conformal risk control (TRACE-CRC), a method for trajectory-aware uncertainty quantification in multi-step CSI prediction. TRACE-CRC constructs Frobenius-norm uncertainty balls around predicted CSI matrices and controls the risk that at least one future frame is uncovered. Instead of calibrating each future step independently, TRACE-CRC combines future-step-dependent error profiling, trajectory difficulty stratification, and learn-then-test (LTT) risk control. Empirically, TRACE-CRC achieves reliable trajectory-level coverage with substantially smaller uncertainty balls than conservative multi-step corrections, while avoiding the trajectory undercoverage of compact stepwise and adaptive conformal baselines.
