Dear All,
 
We have the pleasure of inviting you to the Particle Theory Seminar on Tuesday, March 26 at 12:15, which will be given by

Indaco Biazzo (Polytechnique de Lausanne)

entitled

„Boltzmann Autoregressive Neural Networks".

Abstract:

Generative Autoregressive Neural Networks (ARNNs) excel in generative tasks across various domains, including images, language, and science. Particularly in physics, they have successfully applied to generate samples from statistical physics models.  Despite their success, ARNN architectures often operate as black boxes without a clear connection to underlying physics or statistical models. This seminar explores the direct link between neural network architectures and physics models. I'll show how the neural network parameters align with Hamiltonian couplings and external fields, highlighting the emergence of residual connections and recurrent architectures from the derivation. By leveraging statistical physics techniques, we formulate ARNNs for specific systems, and I’ll discuss a new approach for sampling from sparse interacting systems, crucial for physics, optimization, and inference problems. Our findings validate a physically informed approach and suggest potential extensions to multi-valued variables, paving the way for broader applications in scientific research.

References:

[1] Biazzo, Indaco. "The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems." Communications Physics 6.1 (2023): 296.

[2] Biazzo, Indaco, Dian Wu, and Giuseppe Carleo. "Sparse Autoregressive Neural Networks for Classical Spin Systems." arXiv preprint arXiv:2402.16579 (2024).

The speaker will be on-line, local participants are invited to meet in the seminar room D-2-02.