516 citations · 921 across the 41 of their papers we have counts for
42 papers
Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation
Andrea Basteri, Carlo Ciliberto, Alessandro Rudi
Missing values undermine statistical inference and machine learning pipelines, yet most imputation methods rely on heuristics or restrictive parametric assumptions that ignore the…
Lookahead identification in adversarial bandits: accuracy and memory bounds
Nataly Brukhim, Nicolò Cesa-Bianchi, Carlo Ciliberto
We study an identification problem in multi-armed bandits. In each round a learner selects one of arms and observes its reward, with the goal of eventually identifying an arm t…
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)…
Closed-form Filtering for Non-linear Systems
Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj +1
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…
Robust Meta-Representation Learning via Global Label Inference and Classification
Ruohan Wang, Isak Falk, Massimiliano Pontil +1
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…
Schedule-Robust Online Continual Learning
Ruohan Wang, Marco Ciccone, Giulia Luise +3
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…