paper-with-me

Papers

CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning

2026-03-17 · Weikun K. Zhang, Rohan Pandey, Bhaumik Mehta, Kaijie Jin, Naomi Morato, Archit Ganapule, Michael Ruofan Zeng, Jarod Alper arxiv

Motivated by auto-proof generation and Valiant's VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to compute polynomials, using addition and multiplication gates. We formulate this problem as a single-player game, where an RL agent attempts to build the circuit within a fixed number of operations. We implement an AlphaZero-style training loop and compare two approaches: Proximal Policy Optimization with Monte Carlo Tree Search (PPO+MCTS) and Soft Actor-Critic (SAC). SAC achieves the highest success rates on two-variable targets, while PPO+MCTS scales to three variables and demonstrates steady improvement on harder instances. These results suggest that polynomial circuit synthesis is a compact, verifiable setting for studying self-improving search policies.

📄 PDF Abstract BibTeX arXiv:2603.17075

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

FactorLibrary: From Polynomials to Circuits via Recursive Subgoals

2026-06-24 · Rohan Pandey, Michael Ruofan Zeng, Weikun K. Zhang, Kaijie Jin 외 arxiv

Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory. We formulate it as a reinforcement learning problem in two directions, bott…

Reinforcement Learning

Polynomial Semantics of Tractable Probabilistic Circuits

2024-02-14 · Oliver Broadrick, Honghua Zhang, Guy Van Den Broeck

Probabilistic circuits compute multilinear polynomials that represent multivariate probability distributions. They are tractable models that support efficient marginal inference. However, various polynomial semantics hav…

Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials

2024-02-26 · Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo

Grokking has been actively explored to reveal the mystery of delayed generalization and identifying interpretable representations and algorithms inside the grokked models is a suggestive hint to understanding its mechani…

Hardness of Random Optimization Problems for Boolean Circuits, Low-Degree Polynomials, and Langevin Dynamics

2020-04-25 · David Gamarnik, Aukosh Jagannath, Alexander S. Wein

We consider the problem of finding nearly optimal solutions of optimization problems with random objective functions. Two concrete problems we consider are (a) optimizing the Hamiltonian of a spherical or Ising $p$-spin …

Efficient reconstruction of depth three circuits with top fan-in two

2021-03-12 · Gaurav Sinha

We develop efficient randomized algorithms to solve the black-box reconstruction problem for polynomials over finite fields, computable by depth three arithmetic circuits with alternating addition/multiplication gates, s…

Vocal Bursts Valence Prediction