On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “IWCNN”

Provably Convergent Data-Driven Convex-Nonconvex Regularizationcs.LG

New method uses deep learning to solve inverse problems with provable guarantees.

problem Solving inverse problems with high-quality results and provable guarantees.

method Convex-Nonconvex (CNC) framework with input weakly convex neural network (IWCNN).

result The method provides provably convergent regularization for inverse problems.

inverse problems deep learning provably convergent CNC framework IWCNN

2023-10-09abs ↗pdf ↗

Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisationmath.OC

This paper improves inverse problem solving with weakly convex regularisers and proves convergence.

problem Improving solution methods for inverse problems.

method Generalised formulation of convergent regularisation using weakly convex regularisers, and proof of convergence for primal-dual hybrid gradient method.

result Proves convergence of primal-dual hybrid gradient method for variational problems and shows improved performance with IWCNNs.

inverse problems weakly convex regularisers convergence primal-dual hybrid gradient method Kurdyka-Lojasiewicz condition

2024-02-01abs ↗pdf ↗