Search Results for author:
Found 8 papers, 0 papers with code
Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds
The privacy preserving properties of Langevin dynamics with additive isotropic noise have been extensively studied.
Data-driven initialization of deep learning solvers for Hamilton-Jacobi-Bellman PDEs
A deep learning approach for the approximation of the Hamilton-Jacobi-Bellman partial differential equation (HJB PDE) associated to the Nonlinear Quadratic Regulator (NLQR) problem.
On Flat Minima, Large Margins and Generalizability
The intuitive connection to robustness and convincing empirical evidence have made the flatness of the loss surface an attractive measure of generalizability for neural networks.
On stochastic mirror descent with interacting particles: convergence properties and variance reduction
A second alternative is to use a fixed step-size and run independent replicas of the algorithm and average these.
Towards Robust and Stable Deep Learning Algorithms for Forward Backward Stochastic Differential Equations
Applications in quantitative finance such as optimal trade execution, risk management of options, and optimal asset allocation involve the solution of high dimensional and nonlinear Partial Differential Equations (PDEs).
The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?
As a first step towards understanding this question we formalize it as an optimization problem with weakly interacting agents.
Predict Globally, Correct Locally: Parallel-in-Time Optimal Control of Neural Networks
We exploit the links between dynamical systems, optimal control, and neural networks to develop a novel distributed optimization algorithm.
MAGMA: Multi-level accelerated gradient mirror descent algorithm for large-scale convex composite minimization
Composite convex optimization models arise in several applications, and are especially prevalent in inverse problems with a sparsity inducing norm and in general convex optimization with simple constraints.
