convergence analysis 1distribution shift 1finite-difference estimation 1gradient-based optimization 1performative prediction 1
From the 1 of 2 linked papers with an AI index.
2 papers
math.OC2026
Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction
Hiroki Hamaguchi, Yuya Hikima, Hiroshi Sawada +1
The paper proposes a gradient-based optimization algorithm that estimates distribution shifts via finite differences, providing convergence guarantees for a wider range of loss fun…
cs.LG2025
FedPM: Federated Learning Using Second-order Optimization with Preconditioned Mixing of Local Parameters
Hiro Ishii, Kenta Niwa, Hiroshi Sawada +3
We propose Federated Preconditioned Mixing (FedPM), a novel Federated Learning (FL) method that leverages second-order optimization. Prior methods--such as LocalNewton, LTDA, and F…