17 citations · 26 across the 18 of their papers we have counts for
20 papers
Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback
Vladimir R. Kostic, Karim Lounici, Hélène Halconruy +3
Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimensional structure, evolving o…
Learning Conditional Expectation Operators via Functional Newton Updates
Thiago Ramos, Alek Fröhlich, Daniel Perazzo +1
We introduce the Functional Spectral-Newton Method (FSNM) for learning the leading singular structure of a conditional expectation operator without fixing a basis or reproducing ke…
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…
Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulation
Max Siebenborn, Daniel Ordoñez Apraez, Sophie Lueth +4
Mobile manipulation requires coordinated control of high-dimensional, bimanual robots. Imitation learning methods have been broadly used to solve these robotic tasks, yet typically…
Toeplitz Based Spectral Methods for Data-driven Dynamical Systems
Vladimir R. Kostic, Karim Lounici, Massimiliano Pontil
We introduce a Toeplitz-based framework for data-driven spectral estimation of linear evolution operators in dynamical systems. Focusing on transfer and Koopman operators from equi…
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…
Toward Scalable and Valid Conditional Independence Testing with Spectral Representations
Alek Fröhlich, Vladimir R. Kostic, Karim Lounici +3
Conditional independence (CI) is central to causal inference, feature selection, and graphical modeling, yet it is untestable in many settings without additional assumptions. Exist…
Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression
Dimitri Meunier, Jakub Wornbard, Vladimir R. Kostic +5
We address the problem of causal effect estimation in the presence of hidden confounders using nonparametric instrumental variable (IV) regression. An established approach is to us…
Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil
This paper provides data-dependent bounds on the expected error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained fo…
The seeds of the future are in the present: A blind exploration of metastable states
Timothée Devergne, Vladimir Kostic, Massimiliano Pontil +1
In this work, we present a novel type of molecular dynamics simulation that aims at discovering, in a blind way, new metastable states. Using only data coming from an initial unbia…
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…
Representation Learning for Equivariant Inference with Guarantees
Daniel Ordoñez-Apraez, Vladimir Kostić, Alek Fröhlich +3
In many real-world applications of regression, conditional probability estimation, and uncertainty quantification, exploiting symmetries rooted in physics or geometry can dramatica…
QuantFormer: Learning to Quantize for Neural Activity Forecasting in Mouse Visual Cortex
Salvatore Calcagno, Isaak Kavasidis, Simone Palazzo +8
Understanding complex animal behaviors hinges on deciphering the neural activity patterns within brain circuits, making the ability to forecast neural activity crucial for developi…
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…
From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach
Timothée Devergne, Vladimir Kostic, Michele Parrinello +1
We investigate learning the eigenfunctions of evolution operators for time-reversal invariant stochastic processes, a prime example being the Langevin equation used in molecular dy…
Leveraging Symmetry in RL-based Legged Locomotion Control
Zhi Su, Xiaoyu Huang, Daniel Ordoñez-Apraez +8
Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information of th…
Morphological Symmetries in Robotics
Daniel Ordoñez-Apraez, Giulio Turrisi, Vladimir Kostic +6
We present a comprehensive framework for studying and leveraging morphological symmetries in robotic systems. These are intrinsic properties of the robot's morphology, frequently o…
Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport
Vladimir Kostic, Saverio Salzo, Massimilano Pontil
In this work we propose a batch version of the Greenkhorn algorithm for multimarginal regularized optimal transport problems. Our framework is general enough to cover, as particula…