4 papers
CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency
Hirofumi Ota, Naoto Iwase, Yuki Ichihara +2
Large language models often improve reasoning by sampling multiple outputs and aggregating their final answers, but precise and efficient control of error levels remains a challeng…
Federated Learning with Relative Fairness
Shogo Nakakita, Tatsuya Kaneko, Shinya Takamaeda-Yamazaki +1
This paper proposes a federated learning framework designed to achieve \textit{relative fairness} for clients. Traditional federated learning frameworks typically ensure absolute f…
Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution
Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi
We consider a variant of the stochastic gradient descent (SGD) with a random learning rate and reveal its convergence properties. SGD is a widely used stochastic optimization algor…
Dimension-free Bounds for Sum of Dependent Matrices and Operators with Heavy-Tailed Distribution
Shogo Nakakita, Pierre Alquier, Masaaki Imaizumi
We prove deviation inequalities for sums of high-dimensional random matrices and operators with dependence and {\rc heavy tails}. Estimation of high-dimensional matrices is a conce…