Statistical Learning
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Lipschitzness, which we make precise in Section 2 and in Assumption 3.1.
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Our preliminary results suggest that the regularized exponential mechanism can effectively emulate previous empirical and population risk bounds, negating the need for smoothness assumptions for algorithms with polynomial running time.
The Space Complexity of Approximating Logistic Loss
D () has lower space complexity than the original problem or can be minimized more efficiently.
Derandomized novelty detection with FDR control via conformal e-values
Instead, we apply powerful machine learning models for one-class (Moya et al., 1993) or
