Workshops

Understanding machine learning via exactly solvable statistical physics models

Capacity-resolution trade-off in the optimal learning of multiple low-dimensional manifolds by attractor neural networks

Trainability and accuracy of artificial neural networks

Covariant neural network architectures for learning physics

Machine learning for atomic and molecular simulations

Energy-Based Self-Supervised Learning

Which is worse: a weak signal lost in entropy or trapping by topological complexity?

High-dimensional cost landscape and gradient descent in Tensor PCA and its generalisations

Quantum annealing and machine learning - new directions of quantum

Statistical Mechanics of Deep Manifolds: Mean Field Geometry in High Dimension

Evidence of local entropy optimization in machine learning, physics and neuroscience

Deep learning as a toy model of the 1/N-expansion and renormalization

On the existence of wide flat minima in neural network landscapes: analytic and algorithm approaches

Innovating machine learning with near-term quantum computing

Boltzmann Trees: a physically inspired randomization for robust modeling of physical data

Thermodynamic limits for neural networks

Machine learning with neural networks: the importance of data structure

Graph neural networks for combinatorial optimization problems on graphs

Subgroup Discovery for Assessing the Domain of Applicability of Machine Learning Models

How to assess scientific machine learning models? Prediction errors and predictive uncertainty quantification

Spectral Methods and the Landscapes of High-Dimensional Inference Problems

Representation and regression problems for molecular structure and dynamics

Bayesian Experimental Design in the Physical Sciences