44 citations · 155 across the 9 of their papers we have counts for
9 papers
Cheng's eigenvalue comparison on metric measure spaces and applications
G. Bruno De Luca, Nicolò De Ponti, Andrea Mondino +1
Using the localization technique, we prove a sharp upper bound on the first Dirichlet eigenvalue of metric balls in essentially non-branching spaces. Thi…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1167
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Improving Energy Conserving Descent for Machine Learning: Theory and Practice
G. Bruno De Luca, Alice Gatti, Eva Silverstein
We develop the theory of Energy Conserving Descent (ECD) and introduce ECDSep, a gradient-based optimization algorithm able to tackle convex and non-convex optimization problems. T…
Microcanonical Hamiltonian Monte Carlo
Jakob Robnik, G. Bruno De Luca, Eva Silverstein +1
We develop Microcanonical Hamiltonian Monte Carlo (MCHMC), a class of models which follow a fixed energy Hamiltonian dynamics, in contrast to Hamiltonian Monte Carlo (HMC), which f…
Born-Infeld (BI) for AI: Energy-Conserving Descent (ECD) for Optimization
G. Bruno De Luca, Eva Silverstein
We introduce a novel framework for optimization based on energy-conserving Hamiltonian dynamics in a strongly mixing (chaotic) regime and establish its key properties analytically…
Hyperbolic compactification of M-theory and de Sitter quantum gravity
G. Bruno De Luca, Eva Silverstein, Gonzalo Torroba
We present a mechanism for accelerated expansion of the universe in the generic case of negative-curvature compactifications of M-theory, with minimal ingredients. M-theory on a hy…