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.
The paper defines Fenchel conjugate and biconjugate on Hadamard manifolds.
Generalizes Fenchel conjugation to nonlinear functions on arbitrary sets.
The paper finds local minimizers for obstacle avoidance on curved spaces.
SAM improves deep learning by relaxing Bayes objective.
Regularized empirical risk minimization with constrained labels (in contrast to fixed labels) is a remarkably general abstraction of learning. For common loss and regularization functions, this optimization problem assumes the form of a mixed integer program (MIP) whose objective function is non-convex. In this form, t…