Parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), are known
to enhance training efficiency in Large Language Models (LLMs). Due to the limited …

Existing work in scientific machine learning (SciML) has shown that data-driven learning of
solution operators can provide a fast approximate alternative to classical numerical partial …

The Cold Posterior Effect (CPE) is a phenomenon in Bayesian Deep Learning (BDL), where
tempering the posterior to a cold temperature often improves the predictive performance of …

Modern training strategies of deep neural networks (NNs) tend to induce a heavy-tailed (HT)
spectra of layer weights. Extensive efforts to study this phenomenon have found that NNs …

Deep learning is renowned for its theory-practice gap, whereby principled theory typically
fails to provide much beneficial guidance for implementation in practice. This has been …

Double-descent refers to the unexpected drop in test loss of a learning algorithm beyond an
interpolating threshold with over-parameterization, which is not predicted by information …

State of the art neural networks provide a rich class of function approximators, fueling the
remarkable success of gradient-based deep learning on complex high-dimensional …

Existing work in scientific machine learning (SciML) has shown that data-driven learning of
solution operators can provide a fast approximate alternative to classical numerical partial …

We perform statistical inference for the solution of stochastic optimization problems with
equality and box inequality constraints. The considered problems are prevalent in statistics …