no code implementations • ICML 2020 • Riccardo Grazzi, Saverio Salzo, Massimiliano Pontil, Luca Franceschi
We study a general class of bilevel optimization problems, in which the upper-level objective is defined via the solution of a fixed point equation.
no code implementations • 18 Mar 2024 • Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
We study the problem of efficiently computing the derivative of the fixed-point of a parametric nondifferentiable contraction map.
no code implementations • 21 Aug 2023 • Marianna de Santis, Jordan Frecon, Francesco Rinaldi, Saverio Salzo, Martin Schmidt
In recent years, bilevel approaches have become very popular to efficiently estimate high-dimensional hyperparameters of machine learning models.
no code implementations • 18 Aug 2023 • Cheik Traoré, Vassilis Apidopoulos, Saverio Salzo, Silvia Villa
Stochastic proximal point algorithms have been studied as an alternative to stochastic gradient algorithms since they are more stable with respect to the choice of the stepsize but a proper variance reduced version is missing.
no code implementations • 17 Aug 2022 • Daniela A. Parletta, Andrea Paudice, Massimiliano Pontil, Saverio Salzo
In this work we study high probability bounds for stochastic subgradient methods under heavy tailed noise.
2 code implementations • NeurIPS 2023 • Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
We analyse a general class of bilevel problems, in which the upper-level problem consists in the minimization of a smooth objective function and the lower-level problem is to find the fixed point of a smooth contraction map.
no code implementations • 1 Dec 2021 • Vladimir Kostic, Saverio Salzo, Massimilano Pontil
In this work we propose a batch version of the Greenkhorn algorithm for multimarginal regularized optimal transport problems.
no code implementations • 5 Jan 2021 • Vladimir Kostic, Saverio Salzo
We analyze in depth the case of affine feasibility problems showing that the iterates generated by the proposed methods converge Q-linearly and providing also explicit global and local rates of convergence.
Optimization and Control 90C25, 65K05, 49M37, 90C15, 90C06
no code implementations • 13 Nov 2020 • Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo
Bilevel optimization problems are receiving increasing attention in machine learning as they provide a natural framework for hyperparameter optimization and meta-learning.
1 code implementation • 29 Jun 2020 • Riccardo Grazzi, Luca Franceschi, Massimiliano Pontil, Saverio Salzo
We study a general class of bilevel problems, consisting in the minimization of an upper-level objective which depends on the solution to a parametric fixed-point equation.
no code implementations • 23 Mar 2020 • Feliks Hibraj, Marcello Pelillo, Saverio Salzo, Massimiliano Pontil
Second, we use a Nystrom-type subsampling approach, which allows for a training phase with a smaller number of data points, so to reduce the computational cost.
1 code implementation • NeurIPS 2019 • Giulia Luise, Saverio Salzo, Massimiliano Pontil, Carlo Ciliberto
We present a novel algorithm to estimate the barycenter of arbitrary probability distributions with respect to the Sinkhorn divergence.
no code implementations • NeurIPS 2018 • Jordan Frecon, Saverio Salzo, Massimiliano Pontil
Regression with group-sparsity penalty plays a central role in high-dimensional prediction problems.
2 code implementations • 13 Jun 2018 • Luca Franceschi, Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo, Paolo Frasconi
In (Franceschi et al., 2018) we proposed a unified mathematical framework, grounded on bilevel programming, that encompasses gradient-based hyperparameter optimization and meta-learning.
no code implementations • ICML 2018 • Luca Franceschi, Paolo Frasconi, Saverio Salzo, Riccardo Grazzi, Massimilano Pontil
We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning.
1 code implementation • 12 Feb 2018 • Federico Tomasi, Veronica Tozzo, Saverio Salzo, Alessandro Verri
The estimation of the contribution of the latent factors is embedded in the model which produces both sparse and low-rank components for each time point.
no code implementations • 18 Jul 2017 • Saverio Salzo, Johan A. K. Suykens, Lorenzo Rosasco
In this paper, we discuss how a suitable family of tensor kernels can be used to efficiently solve nonparametric extensions of $\ell^p$ regularized learning methods.
no code implementations • 18 Mar 2016 • Saverio Salzo, Johan A. K. Suykens
In this paper we study the variational problem associated to support vector regression in Banach function spaces.