Despite their successes, machine learning techniques are often stochastic, error-prone and
blackbox. How could they then be used in fields such as theoretical physics and pure …

We aim to understand grokking, a phenomenon where models generalize long after
overfitting their training set. We present both a microscopic analysis anchored by an effective …

Variational quantum circuits are used in quantum machine learning and variational quantum
simulation tasks. Designing good variational circuits or predicting how well they perform for …

We study the conformal bootstrap of 1D CFTs on the straight Maldacena–Wilson line in 4D
N= 4 super-Yang–Mills theory. We introduce an improved truncation scheme with an “OPE …

Bayesian neural networks are theoretically well-understood only in the infinite-width limit,
where Gaussian priors over network weights yield Gaussian priors over network outputs …

Both the path integral measure in field theory (FT) and ensembles of neural networks (NN)
describe distributions over functions. When the central limit theorem can be applied in the …

Recent works have suggested that finite Bayesian neural networks may sometimes
outperform their infinite cousins because finite networks can flexibly adapt their internal …

Understanding how feature learning affects generalization is among the foremost goals of
modern deep learning theory. Here, we study how the ability to learn representations affects …

Can artificial intelligence learn mathematics? The question is at the heart of this original
monograph bringing together theoretical physics, modern geometry, and data science. The …

We present a stringy realization of quantum field theory ensembles in D≤ 4 spacetime
dimensions, thus realizing a disorder averaging over coupling constants. When each …