---
title: "Beyond Accuracy: Information-Theoretic Decoder Evaluation Under Latent Intent"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05658v1"
permalink: "https://feed.astralor.com/items/itm_9b27e346f8169ce57eba25e5"
published: "2026-11-03T21:43:43.000Z"
score: 60
channel: "ai"
tags: ["Beyond Accuracy","Information-Theoretic Decoder Evaluation","Under Latent Intent","Prior","Since","Markov","POMDP"]
---

# Beyond Accuracy: Information-Theoretic Decoder Evaluation Under Latent Intent

## 速览

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…

## 关键点

- 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.

## 全文

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 $Γ_{\min}$ sets this boundary. Then, we derive a closed-form regret predictor $U_{\mathrm{id}}(C)$, that can be computed from any confusion matrix in $O(K^2)$ time. Across two domains spanning orthogonal information channels, we show that $U_{\mathrm{id}}$ 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 $9.6\times$ in held-out regret, which $U_{\mathrm{id}}$ predicts. Same-signal control confirms $U_{\mathrm{id}}$'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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_9b27e346f8169ce57eba25e5