cs.LGNov 3, 2026

Beyond Accuracy: Information-Theoretic Decoder Evaluation Under Latent Intent

Authors: Tasha Kim, Benjamin Ballyk, Anson Lei, Ingmar Posner, Oiwi Parker Jones

Organizations: University of Oxford

Abstract

A central challenge in assistive brain-to-robot control is decoding a user's latent intent from complex and noisy brain signals. Prior approaches evaluate decoders as single-trial classifiers with accuracy-based metrics, but this neglects the inherently sequential nature of assistive control. Since a planner must integrate intermittent, noisy decoder outputs over time, single-step accuracy can only be a proxy when predicting downstream task performance. We formalize brain-to-robot control as a partially observable Markov decision process (POMDP), and prove that there is a sharp phase transition: regret is uniformly bounded across the horizon as long as pairs of goals are all decoder-distinguishable, but grows linearly otherwise. We show that a single channel statistic, the worst-pair Chernoff information Γmin⁡Γ_{\min} sets this boundary. Then, we derive a closed-form regret predictor Uid(C)U_{\mathrm{id}}(C), that can be computed from any confusion matrix in O(K2)O(K^2) time. Across two domains spanning orthogonal information channels, we show that UidU_{\mathrm{id}} predicts cumulative planning regret beyond what accuracy can explain. We then highlight a pathological accuracy trap, in which two decoders have identical validation accuracy 35.1% on real EEG data (BNCI2014001 subject 5) but result in a difference of 9.6×9.6\times in held-out regret, which UidU_{\mathrm{id}} predicts. Same-signal control confirms UidU_{\mathrm{id}}'s advantage with decoders that span independent feature channels. Ultimately, our work provides a drop-in diagnostic to evaluate and select sensors and decoders in sequential assistive control.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EEG-Driven Intention Decoding: Offline Deep Learning Benchmarking on a Robotic Rover

    Feb 23, 2026Ghadah Alosaimi, Maha Alsayyari, Yixin Sun +3Brain-Computer InterfacesEEG Decoding

  2. DECODE: Decomposable Environments for COntrolled Sequential-Decision Evaluation

    Nov 13, 2026Diego Silva Prado, Bruno Caldas de Souza, Tiago Amaral Penteado de Jesus +3Sequential Decision MakingPartially Observable Markov Decision Processes

  3. Bayesian control for coding agents

    Jun 23, 2026Theodore Papamarkou, Vladislav Smirnov, Viktor Mazanov +4Language Model-Based ControlCoding Agents