3 accepted papers
In this work, we propose *Natural Hypergradient Descent* (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation—namely, the need to compute or approximate Hessian inverses—we exploit the statistical structure of the inner o…
This paper studies the generalization bounds for the empirical saddle point (ESP) solution to stochastic saddle point (SSP) problems. For SSP with Lipschitz continuous and strongly convex-strongly concave objective functions, we establish an $O\left(1/n\right)$ generalization bound by using a probab…
In this paper, we consider online learning with non-convex loss functions. Similar to Besbes et al. [2015] we apply non-stationary regret as the performance metric. In particular, we study the regret bounds under different assumptions on the information available regarding the loss functions. When t…