paper-with-me

홈 › Papers

Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks

2026-02-27 · Sai Sandeep Damera, Ryan Matheu, Aniruddh G. Puranic, John S. Baras arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.00302

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks

2026-05-23 · Sai Sandeep Damera, Ryan Matheu, Aniruddh G. Puranic, John S. Baras 외 arxiv

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

2026-01-20 · Gorgi Pavlov arxiv

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

2025-11-21 · Chandrasekhar Gokavarapu, D. Madhusudhana Rao arxiv

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 Graphs

A Kolmogorov-Arnold Surrogate Model for Chemical Equilibria: Application to Solid Solutions

2026-03-16 · Leonardo Boledi, Dirk Bosbach, Jenna Poonoosamy arxiv

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

2022-11-22 · Ahmet Unutulmaz, Cem Ünsalan

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…