In this paper, a restricted memory quasi-Newton bundle method for minimizing a locally Lipschitz function over a Riemannian manifold is proposed, which extends the classical one in Euclidean spaces to the manifold setting. The curvature information of the objective function is approximated by applying the Riemannian version of the quasi-Newton updating formulas. The subgradient aggregation technique is used to avoid solving the time-consuming quadratic programming subproblem when calculating the candidate descent direction. Moreover, a new Riemannian line search procedure is proposed to generate the stepsizes, and the process is finitely terminated under a new version of the Riemannian semismooth assumption. Global convergence of the proposed method is established: if the serious iteration steps are finite, then the last serious iterate is stationary; otherwise, every accumulation point of the serious iteration sequence is stationary. Finally, some preliminary numerical results show that the proposed method is efficient.
