## Abstract

We study identity testing for restricted Boltzmann machines (RBMs), and more generally for undirected graphical models. Given sample access to the Gibbs distribution corresponding to an unknown or hidden model M^{∗} and given an explicit model M, can we distinguish if either M = M^{∗} or if they are (statistically) far apart? Daskalakis et al. (2018) presented a polynomial-time algorithm for identity testing for the ferromagnetic (attractive) Ising model. In contrast, for the antiferromagnetic (repulsive) Ising model, Bezáková et al. (2019) proved that unless RP = NP there is no identity testing algorithm when βd = ω(log n), where d is the maximum degree of the visible graph and β is the largest edge weight (in absolute value). We prove analogous hardness results for RBMs (i.e., mixed Ising models on bipartite graphs), even when there are no latent variables or an external field. Specifically, we show that if RP 6= NP, then when βd = ω(log n) there is no polynomial-time algorithm for identity testing for RBMs; when βd = O(log n) there is an efficient identity testing algorithm that utilizes the structure learning algorithm of Klivans and Meka (2017). In addition, we prove similar lower bounds for purely ferromagnetic RBMs with inconsistent external fields, and for the ferromagnetic Potts model. Previous hardness results for identity testing of Bezáková et al. (2019) utilized the hardness of finding the maximum cuts, which corresponds to the ground states of the antiferromagnetic Ising model. Since RBMs are on bipartite graphs such an approach is not feasible. We instead introduce a novel methodology to reduce from the corresponding approximate counting problem and utilize the phase transition that is exhibited by RBMs and the mean-field Potts model. We believe that our method is general, and that it can be used to establish the hardness of identity testing for other spin systems.

Original language | English (US) |
---|---|

Pages (from-to) | 514-529 |

Number of pages | 16 |

Journal | Proceedings of Machine Learning Research |

Volume | 125 |

State | Published - 2020 |

Event | 33rd Conference on Learning Theory, COLT 2020 - Virtual, Online, Austria Duration: Jul 9 2020 → Jul 12 2020 |

## All Science Journal Classification (ASJC) codes

- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability