Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks
Differentiable logic gate networks (DLGNs) learn compact, interpretable Boolean circuits via gradient-based training, but all existing variants are restricted to the 16 two-input binary gates. Extending DLGNs to Ternary Kleene $K_3$ logic and training DTLGNs where the UNKNOWN state enables principled abstention under uncertainty is desirable. However, the support set of potential gates per neuron explodes to $19{,}683$, making the established softmax-over-gates training approach intractable. We introduce Polynomial Surrogate Training (PST), which represents each ternary neuron as a degree-$(2,2)$ polynomial with 9 learnable coefficients (a $2{,}187\times$ parameter reduction) and prove that the gap between the trained network and its discretized logic circuit is bounded by a data-independent commitment loss that vanishes at convergence. Scaling experiments from 48K to 512K neurons on CIFAR-10 demonstrate that this hardening gap contracts with overparameterization. Ternary networks train $2$-$3\times$ faster than binary DLGNs and discover true ternary gates that are functionally diverse. On synthetic and tabular tasks we find that the UNKNOWN output acts as a Bayes-optimal uncertainty proxy, enabling selective prediction in which ternary circuits surpass binary accuracy once low-confidence predictions are filtered. More broadly, PST establishes a general polynomial-surrogate methodology whose parameterization cost grows only quadratically with logic valence, opening the door to many-valued differentiable logic.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks
Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as runtime monitors in safety-critical systems demands more than predictive …
Differentiable Logic Synthesis: Spectral Coefficient Selection via Sinkhorn-Constrained Composition
Learning precise Boolean logic via gradient descent remains challenging: neural networks typically converge to "fuzzy" approximations that degrade under quantization. We introduce Hierarchical Spectral Composition, a dif…
Ternary Gamma Semirings as a Novel Algebraic Framework for Learnable Symbolic Reasoning
Binary semirings such as the tropical, log, and probability semirings form a core algebraic tool in classical and modern neural inference systems, supporting tasks like Viterbi decoding, dynamic programming, and probabil…
Knowledge GraphsA Kolmogorov-Arnold Surrogate Model for Chemical Equilibria: Application to Solid Solutions
The computational cost of geochemical solvers is a challenging matter. For reactive transport simulations, where chemical calculations are performed up to billions of times, it is crucial to reduce the total computationa…
Implementation and Applications of a Ternary Threshold Logic Gate
Reducing delay, power consumption, and chip area of a logic circuit are the main targets of a designer. Most of the times, the designer sacrifices power consumption and chip area to improve delay for a given technology n…