5 papers
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
Tommaso Mencattini, Francesco Montagna, Francesco Locatello
Sparse Autoencoders (SAEs) that can accurately reconstruct their input (minimizing distortion) by making efficient use of few features (minimizing the rate) often fail to learn mon…
Causal Learning with the Invariance Principle
Francesco Montagna, Francesco Locatello
Causal discovery, the problem of inferring the direction of causality, is generally ill-posed. We use the language of structural causal models (SCM) to show that assuming that the…
On the Identifiability of Causal Graphs with the Invariance Principle
Francesco Montagna
Causal discovery from i.i.d. observational data is known to be generally ill-posed. We demonstrate that if we have access to the distribution {induced} by a structural causal model…
Score matching through the roof: linear, nonlinear, and latent variables causal discovery
Francesco Montagna, Philipp M. Faller, Patrick Bloebaum +2
Causal discovery from observational data holds great promise, but existing methods rely on strong assumptions about the underlying causal structure, often requiring full observabil…
Demystifying amortized causal discovery with transformers
Francesco Montagna, Max Cairney-Leeming, Dhanya Sridhar +1
Supervised learning for causal discovery from observational data often achieves competitive performance despite seemingly avoiding the explicit assumptions that traditional methods…