Lab. Information, Learning and Physics

At IdePHICS, we study problems from computer science, machine learning, statistics and signal processing using many mathematical tools and in particular using ideas from theoretical statistical physics.

Navigating the labyrinth: How AI tackles complex data sampling

09.07.24Research

Researchers at EPFL have made a breakthrough in understanding how neural network-based generative models perform against traditional data sampling techniques in complex systems, unveiling both challenges and opportunities for AI's future in data generation.

IdePHICS @ NeurIPS 2021

18.11.21Research

Four IdePHICS papers have been accepted to thirty-five conference on Neural Information Processing Systems (NeurIPS), putting the lab among the top academic contributors to the conference. Due to Covid-19, this year NeurIPS edition will be a virtual-only conference held from Monday, December 6th through Tuesday, December 124h, 2021. A mirror conference is co-organised by IdePHICS on dec. 6 in EPFL. The accepted IdePHICS papers are as follows:

IdePHICS @ MSML 2021 in Lausanne

18.05.21Research

Two IdePHICS papers have been accepted to the Mathematical and Scientific Machine Learning (MSML 2021) conference in Lausanne. Due to Covid-19, this year MSML edition will be a virtual-only conference held from Aug 16-19th, 2021. The accepted IdePHICS papers are as follows: