Massimiliano Pontil

Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems

Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime

Representation Learning for Equivariant Inference with Guarantees

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues