ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Consider the nonlinear input-output system with BB input-output training pairs (XB,YB)(X_B,Y_B) and its equivalent system, with input vectors xB+1{\mathbf{x}}_{B+1} and xˉ\bar{{\mathbf{x}}} and corresponding observations yB+1{\mathbf{y}}_{B+1} and yˉ\bar{{\mathbf{y}}}. For each transmitter mm, let x^B+1,m\hat{x}_{B+1,m} and xˉ^m\hat{\bar{x}}_m be the respective maximum a posteriori estimates:

x^B+1,m=argmaxxP(xB+1,m=x∣XB,YB,yB+1),xˉ^m=argmaxxP(xˉm=x∣G,yˉ).\hat{x}_{B+1,m}=\mathop{\mathrm{argmax}}_{x}P(x_{B+1,m}=x|X_B,Y_B,{\mathbf{y}}_{B+1}),\qquad \hat{\bar{x}}_m=\mathop{\mathrm{argmax}}_{x}P(\bar{x}_m=x|G,\bar{{\mathbf{y}}}).

Define the average error probabilities

Pe,x=1M∑m=1MEP(xB+1,m≠x^B+1,m∣XB,YB,yB+1),P_{e,x}=\frac{1}{M}\sum_{m=1}^{M}\mathbb{E}P(x_{B+1,m}\neq\hat{x}_{B+1,m}|X_B,Y_B,{\mathbf{y}}_{B+1}), Pˉe,x=1M∑m=1MEP(xˉm≠xˉ^m∣G,yˉ).\bar{P}_{e,x}=\frac{1}{M}\sum_{m=1}^{M}\mathbb{E}P(\bar{x}_m\neq\hat{\bar{x}}_m|G,\bar{{\mathbf{y}}}).

Training-based error-probability equivalence conjecture. For the system with BB input-output training pairs (XB,YB)(X_B,Y_B),

lim⁡T→∞Pe,x=lim⁡T→∞Pˉe,x.\lim_{T\to\infty}P_{e,x}=\lim_{T\to\infty}\bar{P}_{e,x}.

Here xB+1,mx_{B+1,m} and xˉm\bar{x}_m are the mmth elements of the input vectors in the original and equivalent systems, respectively. The conjecture translates the mutual-information equivalence theorem into a prediction for symbol error probabilities; it is stated because it is not proved in the paper, although its consequences are reported to be accurate and useful.

Record

Comments

Nothing has been published against this problem yet, and nothing has been said about it.

Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.

Sign in

Solve with an agent

Open the statement in a chat, with the problem and the ground rules already written into the prompt.

This opens a third-party site. Nothing is posted back to ProbXiv and nothing you write there is recorded here — what a model gives you is an attempt, which a person still has to check.