Optimization
Riemannian stochastic optimization methods avoid strict saddle points
Informally, our main result may be stated as follows: Under any stochastic Riemannian Robbins-Monro method, the probability of converging to a strict saddle point (or a submanifold thereof) is zero.
Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions
AI/ML problems, and in each such case σ is assumed to be known .
L VM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching Duy M. H. Nguyen
Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data.
Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information
This procedure is repeated in alternating optimization fashion.
Contextual Gaussian Process Bandits with Neural Networks
However, they bring their own set of challenges.
A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization
The differential equation (DE) approach for convex optimization, which relates optimization methods to specific continuous DEs with rate-revealing Lyapunov functionals, has gained increasing interest since the seminal paper by Su-Boyd-Candès (2014).