6 papers
SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices
Ernests Lavrinovics, Marco Letizia, Roy Janco +3
We present SigmaScale, a method for learning auxiliary scaling matrices to aid truncated Singular Value Decomposition (SVD) based Large Language Model (LLM) compression. Instea…
Model-Agnostic Signal Discovery with Machine Learning: Bridging the Gap Between Theory and Practice
Oz Amram, Marco Letizia, Mikael Kuusela
Searches for new phenomena in complex scientific data are predominantly model-dependent, optimized for specific hypotheses, and therefore limited in their coverage of the space of…
Learning to Validate Generative Models: a Goodness-of-Fit Approach
Pietro Cappelli, Gaia Grosso, Marco Letizia +2
Generative models are increasingly central to scientific workflows, yet their systematic use and interpretation require a proper understanding of their limitations through rigorous…
Comparing Generative Models with the New Physics Learning Machine
Samuele Grossi, Marco Letizia, Riccardo Torre
The rise of generative models for scientific research calls for the development of new methods to evaluate their fidelity. A natural framework for addressing this problem is two-sa…
Refereeing the Referees: Evaluating Two-Sample Tests for Validating Generators in Precision Sciences
Samuele Grossi, Marco Letizia, Riccardo Torre
We propose a robust methodology to evaluate the performance and computational efficiency of non-parametric two-sample tests, specifically designed for high-dimensional generative m…
Multiple testing for signal-agnostic searches of new physics with machine learning
Gaia Grosso, Marco Letizia
In this work, we address the question of how to enhance signal-agnostic searches by leveraging multiple testing strategies. Specifically, we consider hypothesis tests relying on ma…