3 citations · 3 across the 6 of their papers we have counts for
6 papers
Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization
Corrado Coppola, Lorenzo Papa, Irene Amerini +1
Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these method…
Computational issues in Optimization for Deep networks
Corrado Coppola, Lorenzo Papa, Marco Boresta +2
The paper aims to investigate relevant computational issues of deep neural network architectures with an eye to the interaction between the optimization algorithm and the classific…
CMA Light: a novel Minibatch Algorithm for large-scale non convex finite sum optimization
Corrado Coppola, Giampaolo Liuzzi, Laura Palagi
The supervised training of a deep neural network on a given dataset consists in the unconstrained minimization of the finite sum of continuously differentiable functions, commonly…
Convergence of ease-controlled Random Reshuffling gradient Algorithms under Lipschitz smoothness
Ruggiero Seccia, Corrado Coppola, Giampaolo Liuzzi +1
In this work, we consider minimizing the average of a very large number of smooth and possibly non-convex functions, and we focus on two widely used minibatch frameworks to tackle…
Solving the vehicle routing problem with deep reinforcement learning
Simone Foa, Corrado Coppola, Giorgio Grani +1
Recently, the applications of the methodologies of Reinforcement Learning (RL) to NP-Hard Combinatorial optimization problems have become a popular topic. This is essentially due t…
PUSH: a primal heuristic based on Feasibility PUmp and SHifting
Giorgio Grani, Corrado Coppola, Valerio Agasucci
This work describes PUSH, a primal heuristic combining Feasibility Pump and Shifting. The main idea is to replace the rounding phase of the Feasibility Pump with a suitable adaptat…