对称感知器的邻接猜想和对数正态极限的证明
Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron
摘要:
我们考虑对称二进制感知器模型,这是一种简单的神经网络模型,在统计物理学、信息论和概率论社区中引起了极大的关注,最近与Baldassi等人的学习算法的性能有联系。我们建立了该模型的分拆函数,其期望值规范化,收敛到对数正态分布。因此,这使我们能够为这个模型建立几个假设:(i)它证明了Aubin等人的连续性猜想。19在可满足的制度下,种植和未种植模型之间;(ii)它建立了尖锐的阈值猜想;(iii)它证明了对称情况下的冻结1-RSB猜想,首先由Krauth-Mézard '89在非对称情况下证明。在Perkins-Xu '21最近的工作中,最后两个定理也是通过证明分拆函数在实值函数的分析假设下集中在指数尺度上而建立的。这留下了开放的邻接猜想和对数正态极限特征,这是建立在这里无条件的,验证了分析假设。特别是,我们的证明技术依赖于一个密集的对应部分的小图条件反射方法,这是稀疏模型的罗宾逊和Wormald的著名工作。
英文摘要:
We consider the symmetric binary perceptron model, a simple model of neural networks that has gathered significant attention in the statistical physics, information theory and probability theory communities, with recent connections made to the performance of learning algorithms in Baldassi et al. '15. We establish that the partition function of this model, normalized by its expected value, converges to a lognormal distribution. As a consequence, this allows us to establish several conjectures for this model: (i) it proves the contiguity conjecture of Aubin et al. '19 between the planted and unplanted models in the satisfiable regime; (ii) it establishes the sharp threshold conjecture; (iii) it proves the frozen 1-RSB conjecture in the symmetric case, conjectured first by Krauth-Mézard '89 in the asymmetric case. In a recent work of Perkins-Xu '21, the last two conjectures were also established by proving that the partition function concentrates on an exponential scale, under an analytical assumption on a real-valued function. This left open the contiguity conjecture and the lognormal limit characterization, which are established here unconditionally, with the analytical assumption verified. In particular, our proof technique relies on a dense counter-part of the small graph conditioning method, which was developed for sparse models in the celebrated work of Robinson and Wormald.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。