3 papers
math.ST2026
Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
Max Lovig
In modern parametric model training, full-batch gradient descent (and its variants) suffers due to progressively stronger biasing towards the exact realization of training data; th…
math.ST2025
On Universality of Non-Separable Approximate Message Passing Algorithms
Max Lovig, Tianhao Wang, Zhou Fan
Mean-field characterizations of first-order iterative algorithms -- including Approximate Message Passing (AMP), stochastic and proximal gradient descent, and Langevin diffusions -…
math.ST2025
Almost-Optimal Local-Search Methods for Sparse Tensor PCA
Max Lovig, Conor Sheehan, Konstantinos Tsirkas +1
Local-search methods are widely employed in statistical applications, yet interestingly, their theoretical foundations remain rather underexplored, compared to other classes of est…