Zobrazeno 1 - 10
of 359
pro vyhledávání: '"Pontil, Massimiliano"'
Autor:
Kostic, Vladimir R., Lounici, Karim, Pacreau, Gregoire, Novelli, Pietro, Turri, Giacomo, Pontil, Massimiliano
We introduce NCP (Neural Conditional Probability), a novel operator-theoretic approach for learning conditional distributions with a particular focus on inference tasks. NCP can be used to build conditional confidence regions and extract important st
Externí odkaz:
http://arxiv.org/abs/2407.01171
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) due to the inaccessibility of explicit action-value functions. We addr
Externí odkaz:
http://arxiv.org/abs/2406.19861
We investigate learning the eigenfunctions of evolution operators for time-reversal invariant stochastic processes, a prime example being the Langevin equation used in molecular dynamics. Many physical or chemical processes described by this equation
Externí odkaz:
http://arxiv.org/abs/2406.09028
We study the contextual continuum bandits problem, where the learner sequentially receives a side information vector and has to choose an action in a convex set, minimizing a function associated to the context. The goal is to minimize all the underly
Externí odkaz:
http://arxiv.org/abs/2406.05714
Autor:
Kostic, Vladimir R., Lounici, Karim, Halconruy, Helene, Devergne, Timothee, Pontil, Massimiliano
We address data-driven learning of the infinitesimal generator of stochastic diffusion processes, essential for understanding numerical simulations of natural and physical systems. The unbounded nature of the generator poses significant challenges, r
Externí odkaz:
http://arxiv.org/abs/2405.12940
Autor:
Su, Zhi, Huang, Xiaoyu, Ordoñez-Apraez, Daniel, Li, Yunfei, Li, Zhongyu, Liao, Qiayuan, Turrisi, Giulio, Pontil, Massimiliano, Semini, Claudio, Wu, Yi, Sreenath, Koushil
Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information of the robot's kinematics and dynamics morphology. The under-exploration of
Externí odkaz:
http://arxiv.org/abs/2403.17320
We study the problem of efficiently computing the derivative of the fixed-point of a parametric nondifferentiable contraction map. This problem has wide applications in machine learning, including hyperparameter optimization, meta-learning and data p
Externí odkaz:
http://arxiv.org/abs/2403.11687
Autor:
Ordoñez-Apraez, Daniel, Turrisi, Giulio, Kostic, Vladimir, Martin, Mario, Agudo, Antonio, Moreno-Noguer, Francesc, Pontil, Massimiliano, Semini, Claudio, Mastalli, Carlos
We present a comprehensive framework for studying and leveraging morphological symmetries in robotic systems. These are intrinsic properties of the robot's morphology, frequently observed in animal biology and robotics, which stem from the replicatio
Externí odkaz:
http://arxiv.org/abs/2402.15552
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 randomized adaptation of reduced rank regression, a technique to optimal
Externí odkaz:
http://arxiv.org/abs/2312.17348
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 theory one can evolve any initial distribution of the state forward in t
Externí odkaz:
http://arxiv.org/abs/2312.13426