106 citations · 297 across the 23 of their papers we have counts for
23 papers
Reward-free Pretraining for Reinforcement Learning via Occupancy Coverage Maximization
Marco Pratticò, Pietro Novelli, Massimiliano Pontil +1
Sparse rewards pose a central challenge in reinforcement learning, since agents receive no informative signal until they reach their goal. Intrinsic-reward methods address this iss…
SelfTICA: contrastive learning of dynamical representations for rare-event sampling and characterization
Kai Zhu, Jintu Zhang, Pietro Novelli +2
Rare events govern many important molecular processes but remain difficult to characterize within accessible simulation timescales. This challenge has motivated machine-learning me…
kooplearn: A Scikit-Learn Compatible Library of Algorithms for Evolution Operator Learning
Giacomo Turri, Grégoire Pacreau, Giacomo Meanti +8
kooplearn is a machine-learning library that implements linear, kernel, and deep-learning estimators of dynamical operators and their spectral decompositions. kooplearn can model b…
SpectraFormer: an Attention-Based Raman Unmixing Tool for Accessing the Graphene Buffer-Layer Signature on SiC
Dmitriy Poteryayev, Pietro Novelli, Annalisa Coriolano +7
Raman spectroscopy is a key tool for graphene characterization, yet its application to graphene grown on silicon carbide (SiC) is strongly limited by the intense and variable secon…
Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems
Giacomo Turri, Luigi Bonati, Kai Zhu +2
We introduce an encoder-only approach to learn the evolution operators of large-scale non-linear dynamical systems, such as those describing complex natural phenomena. Evolution op…
Fast and Fourier Features for Transfer Learning of Interatomic Potentials
Pietro Novelli, Giacomo Meanti, Pedro J. Buigues +4
Training machine learning interatomic potentials that are both computationally and data-efficient is a key challenge for enabling their routine use in atomistic simulations. To thi…
Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
Vladimir R. Kostic, Karim Lounici, Hélène Halconruy +3
Markov processes serve as a universal model for many real-world random processes. This paper presents a data-driven approach for learning these models through the spectral decompos…
Neural Conditional Probability for Uncertainty Quantification
Vladimir R. Kostic, Karim Lounici, Gregoire Pacreau +3
We introduce Neural Conditional Probability (NCP), an operator-theoretic approach to learning conditional distributions with a focus on statistical inference tasks. NCP can be used…
Operator World Models for Reinforcement Learning
Pietro Novelli, Marco Pratticò, Massimiliano Pontil +1
Policy Mirror Descent (PMD) is a powerful and theoretically sound methodology for sequential decision-making. However, it is not directly applicable to Reinforcement Learning (RL)…
A randomized algorithm to solve reduced rank operator regression
Giacomo Turri, Vladimir Kostic, Pietro Novelli +1
We present and analyze an algorithm designed for addressing vector-valued regression problems involving possibly infinite-dimensional input and output spaces. The algorithm is a ra…
Consistent Long-Term Forecasting of Ergodic Dynamical Systems
Prune Inzerilli, Vladimir Kostic, Karim Lounici +2
We study the evolution of distributions under the action of an ergodic dynamical system, which may be stochastic in nature. By employing tools from Koopman and transfer operator th…
Dynamics Harmonic Analysis of Robotic Systems: Application in Data-Driven Koopman Modelling
Daniel Ordoñez-Apraez, Vladimir Kostic, Giulio Turrisi +4
We introduce the use of harmonic analysis to decompose the state space of symmetric robotic systems into orthogonal isotypic subspaces. These are lower-dimensional spaces that capt…
Estimating Koopman operators with sketching to provably learn large scale dynamical systems
Giacomo Meanti, Antoine Chatalic, Vladimir R. Kostic +3
The theory of Koopman operators allows to deploy non-parametric machine learning algorithms to predict and analyze complex dynamical systems. Estimators such as principal component…
Learning invariant representations of time-homogeneous stochastic dynamical systems
Vladimir R. Kostic, Pietro Novelli, Riccardo Grazzi +2
We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that f…
Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
John Falk, Luigi Bonati, Pietro Novelli +2
Interatomic potentials learned using machine learning methods have been successfully applied to atomistic simulations. However, accurate models require large training datasets, whi…
Sharp Spectral Rates for Koopman Operator Learning
Vladimir Kostic, Karim Lounici, Pietro Novelli +1
Nonlinear dynamical systems can be handily described by the associated Koopman operator, whose action evolves every observable of the system forward in time. Learning the Koopman o…
Learning dynamical systems: an example from open quantum system dynamics
Pietro Novelli
Machine learning algorithms designed to learn dynamical systems from data can be used to forecast, control and interpret the observed dynamics. In this work we exemplify the use of…
Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces
Vladimir Kostic, Pietro Novelli, Andreas Maurer +3
We study a class of dynamical systems modelled as Markov chains that admit an invariant distribution via the corresponding transfer, or Koopman, operator. While data-driven algorit…
Characterizing metastable states with the help of machine learning
Pietro Novelli, Luigi Bonati, Massimiliano Pontil +1
Present-day atomistic simulations generate long trajectories of ever more complex systems. Analyzing these data, discovering metastable states, and uncovering their nature is becom…
Moiré-Induced Transport in CVD-Based Small-Angle Twisted Bilayer Graphene
Giulia Piccinini, Vaidotas Mišeikis, Pietro Novelli +5
To realize the applicative potential of 2D twistronic devices, scalable synthesis and assembly techniques need to meet stringent requirements in terms of interface cleanness and tw…
Optical and plasmonic properties of twisted bilayer graphene: Impact of interlayer tunneling asymmetry and ground-state charge inhomogeneity
Pietro Novelli, Iacopo Torre, Frank H. L. Koppens +2
We present a theoretical study of the local optical conductivity, plasmon spectra, and thermoelectric properties of twisted bilayer graphene (TBG) at different filling factors and…
Collective excitations in twisted bilayer graphene close to the magic angle
Niels C. H. Hesp, Iacopo Torre, Daniel Rodan-Legrain +14
The electronic properties of twisted bilayer graphene (TBG) can be dramatically different from those of a single graphene layer, in particular when the two layers are rotated relat…
Failure of conductance quantization in two-dimensional topological insulators due to non-magnetic impurities
Pietro Novelli, Fabio Taddei, Andre K. Geim +1
Despite topological protection and the absence of magnetic impurities, two-dimensional topological insulators display quantized conductance only in surprisingly short channels, whi…