QMLTN

Project Activities

Cover Image for Exploring the Variational Ground-State Quantum Adiabatic Theorem: Implications for Quantum Computing

Exploring the Variational Ground-State Quantum Adiabatic Theorem: Implications for Quantum Computing

In this post, I’ll explore the variational ground-state quantum adiabatic theorem and its exciting potential for developing new algorithms tailored for NISQ (Noisy Intermediate-Scale Quantum) devices. By leveraging this theorem, we can enhance the performance of quantum algorithms while navigating the limitations of near-term quantum hardware.

Cover Image for Positive unlabeled learning with tensor networks

Positive unlabeled learning with tensor networks

In this post I describe a tensor network approach to the positive unlabeled learning problem, which achives the state-of-the-art results on the MNIST dataset and categorical datasets.

Cover Image for NeurIPS 2022

NeurIPS 2022

A poster from the NeurIPS 2022 workshops.

Cover Image for Phase transitions in local rule learning

Phase transitions in local rule learning

I will discuss the connection between the perceptron grokking scenario and the problem of learning local rules.

Cover Image for Perceptron grokking

Perceptron grokking

A sudden transition to zero test/generalization error in the terminal training phase in learning algorithmic tasks with deep neural networks (named grokking) has recently attracted a lot of attention. Here we discuss a simple perceptron grokking model with exact analytic solutions.

Cover Image for Symmetry journal Special Issue: Symmetries in Tensor Networks and Its Applications

Symmetry journal Special Issue: Symmetries in Tensor Networks and Its Applications

The journal Symmtery recently started a Special Issue focused on Symmetry in tensor networks and its applications.

Cover Image for Application of deep tensor networks to MNIST and permuted MNIST

Application of deep tensor networks to MNIST and permuted MNIST

In this post I present results on applying deep tensor networks to the MNIST and permuted MNIST classification tasks.

Cover Image for Deep tensor networks with the tensor-network attention layer

Deep tensor networks with the tensor-network attention layer

Tensor networks in machine learning are typically applied as linear models in an exponentially large Hilbert space. In this post, I describe a tensor-network attention layer, which enables us to build deep non-linear tensor-network models.

Cover Image for Improved MPS classifier baselines on simple image datasets

Improved MPS classifier baselines on simple image datasets

In ML research, the baseline models are often not given enough attention when improving existing approaches or implementing new ones. Here we will discuss improving the vanilla matrix product state classifier on simple image datasets by enhancing the data augmentation and the training procedure.

Cover Image for Popular article in Presek: A short overview of quantum machine learning

Popular article in Presek: A short overview of quantum machine learning

A popular science article published in Presek (2021, issue 3, category computer and information science) presenting a short overview of quantum machine learning. A translation of the article can be found below.