Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
AdaGrad-Diff: A New Version of the Adaptive Gradient Algorithm
Matia Bojovic, Saverio Salzo, Massimiliano Pontil
Vanilla gradient methods are often highly sensitive to the choice of stepsize, which typically requires manual tuning. Adaptive methods alleviate this issue and have therefore beco…
stat.ML2025
Convergence Properties of Stochastic Hypergradients
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. A key st…
stat.ML2024
Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates
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. This problem has wide applications in machine lea…