Zobrazeno 1 - 10
of 100
pro vyhledávání: '"Ciliberto, Carlo"'
Detecting and segmenting cracks in infrastructure, such as roads and buildings, is crucial for safety and cost-effective maintenance. In spite of the potential of deep learning, there are challenges in achieving precise results and handling diverse c
Externí odkaz:
http://arxiv.org/abs/2409.02866
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
Sequential Bayesian Filtering aims to estimate the current state distribution of a Hidden Markov Model, given the past observations. The problem is well-known to be intractable for most application domains, except in notable cases such as the tabular
Externí odkaz:
http://arxiv.org/abs/2402.09796
Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has recently become an increasingly popular strategy to significantly improve generalizat
Externí odkaz:
http://arxiv.org/abs/2212.11702
Autor:
Wang, Ruohan, Ciccone, Marco, Luise, Giulia, Yapp, Andrew, Pontil, Massimiliano, Ciliberto, Carlo
A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and have unpr
Externí odkaz:
http://arxiv.org/abs/2210.05561
Autor:
Kostic, Vladimir, Novelli, Pietro, Maurer, Andreas, Ciliberto, Carlo, Rosasco, Lorenzo, Pontil, Massimiliano
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 algorithms to reconstruct such operators are well known, their relationship w
Externí odkaz:
http://arxiv.org/abs/2205.14027
Deep imitation learning requires many expert demonstrations, which can be hard to obtain, especially when many tasks are involved. However, different tasks often share similarities, so learning them jointly can greatly benefit them and alleviate the
Externí odkaz:
http://arxiv.org/abs/2203.14855
Measures of similarity (or dissimilarity) are a key ingredient to many machine learning algorithms. We introduce DID, a pairwise dissimilarity measure applicable to a wide range of data spaces, which leverages the data's internal structure to be inva
Externí odkaz:
http://arxiv.org/abs/2202.05614
The problem of learning functions over spaces of probabilities - or distribution regression - is gaining significant interest in the machine learning community. A key challenge behind this problem is to identify a suitable representation capturing al
Externí odkaz:
http://arxiv.org/abs/2202.03926
Few-shot learning is a central problem in meta-learning, where learners must quickly adapt to new tasks given limited training data. Recently, feature pre-training has become a ubiquitous component in state-of-the-art meta-learning methods and is sho
Externí odkaz:
http://arxiv.org/abs/2108.04055