Recent advances in classical machine learning have shown that creating models with
inductive biases encoding the symmetries of a problem can greatly improve performance …

Quantum machine learning (QML) models are aimed at learning from data encoded in
quantum states. Recently, it has been shown that models with little to no inductive biases (ie …

Quantum neural network architectures that have little to no inductive biases are known to
face trainability and generalization issues. Inspired by a similar problem, recent …

The monitoring of the tassel number and tasseling time reflects the maize growth and is
necessary for crop management. However, it mainly depends on field observations, which is …

Block encoding lies at the core of many existing quantum algorithms. Meanwhile, efficient
and explicit block encodings of dense operators are commonly acknowledged as a …

In learning with recurrent or very deep feed-forward networks, employing unitary matrices in
each layer can be very effective at maintaining long-range stability. However, restricting …

Many quantum algorithms for numerical linear algebra assume black-box access to a block-
encoding of the matrix of interest, which is a strong assumption when the matrix is not …

In light of recently proposed quantum algorithms that incorporate symmetries in the hope of
quantum advantage, we show that with symmetries that are restrictive enough, classical …

Data with geometric structure is ubiquitous in machine learning often arising from
fundamental symmetries in a domain, such as permutation-invariance in graphs and …

In primis, ci tengo a ringraziare i miei relatori, per essere riusciti a guidarmi attraverso questo
percorso nonostante la pandemia e le conseguenti complicazioni. Insieme a loro, tutte le …