Search papers, labs, and topics across Lattice.
This paper develops a four-component accounting framework for finite-state learning devices, delineating the relationships between training-side fit, record correlation, update-side search, and operational capital value. The authors demonstrate that despite increasing record and world correlation, the capital gain can be zero under specific conditions, highlighting the limitations of data-free updates in enhancing value. Additionally, they establish necessary and sufficient conditions for capitalization efficiency and provide insights into value retention during task distribution shifts, emphasizing the nuanced dynamics of memory and learning in finite devices.
A surprising finding reveals that increasing record correlation doesn't necessarily translate to capital gains, challenging assumptions about the efficacy of data-free updates in learning systems.
What a finite learning device has recorded and what will hold value for it on future tasks are not the same quantity. We develop a typed accounting for finite-state learning devices that separates four components: a training-side fit functional $\Phi_{\mathrm{fit}}$, the record-correlation stock $J_{D}=I(M;D)$, an update-side search ledger $\sigma_{M}$, and an operational capital value $V(M;T,b)$. This value is the work gap between an informed protocol class and a blind class obtained by deleting the memory-read port and re-optimizing from scratch. (I) Separation: for every $n$, there is a device family on which record correlation and world correlation grow by $n\ln 2$ while the capital gain is exactly zero. In the $\mathrm{flat}^{*}$ regime, data-free updates never increase $V$. (II) Capitalization ledger: an exact $\mathrm{flat}^{*}$ extraction identity and a universal ledger identity give, for (F5$'$)-stable $M$-local updates under a no-discarded-record-correlation condition (f), the bound $\eta_{\mathrm{cap}}\le 1$ for the capitalization efficiency $\eta_{\mathrm{cap}}=\Delta V/(k T\,\sigma_{M})$, together with necessary and sufficient conditions for equality. (III) Value retention: for the retention gap $L_{\mathrm{gen}}$ and retention ratio $\rho_{\mathrm{gen}}$ (the former carries no sign constraint; the latter is defined for positive training-side value and is not confined to $[0,1]$) we give a two-layer alignment domain: an exact exchange rate between value and the side-information-adjusted record fit $I(M';D\mid Y)$ without any record-side-information independence assumption, and a raw record-stock exchange rate under a joint side-information neutrality condition $(M,D)\perp Y$, whose boundary is marked by an explicit one-time-pad witness. These are statements about finite-device value retention under task-distribution shift, not a theory of statistical generalization.
