Free-rider attacks on model aggregation in federated learning
Free-rider attacks against federated learning consist in dissimulating participation to the
federated learning process with the goal of obtaining the final aggregated model without …
federated learning process with the goal of obtaining the final aggregated model without …
An sde for modeling sam: Theory and insights
We study the SAM (Sharpness-Aware Minimization) optimizer which has recently attracted a
lot of interest due to its increased performance over more classical variants of stochastic …
lot of interest due to its increased performance over more classical variants of stochastic …
On the noisy gradient descent that generalizes as sgd
Convergence rates and approximation results for SGD and its continuous-time counterpart
X Fontaine, V De Bortoli… - Conference on Learning …, 2021 - proceedings.mlr.press
This paper proposes a thorough theoretical analysis of Stochastic Gradient Descent (SGD)
with non-increasing step sizes. First, we show that the recursion defining SGD can be …
with non-increasing step sizes. First, we show that the recursion defining SGD can be …
Shadowing properties of optimization algorithms
Ordinary differential equation (ODE) models of gradient-based optimization methods can
provide insights into the dynamics of learning and inspire the design of new algorithms …
provide insights into the dynamics of learning and inspire the design of new algorithms …