38 citations · 80 across the 10 of their papers we have counts for
12 papers
Interpreting Reinforcement Learning Agents with Susceptibilities
Chris Elliott, Einar Urdshals, David Quarel +1
Susceptibilities are a technique for neural network interpretability that studies the response of posterior expectation values of observables to perturbations of the loss. We gener…
Stagewise Reinforcement Learning and the Geometry of the Regret Landscape
Chris Elliott, Einar Urdshals, David Quarel +2
Singular learning theory characterizes Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as samp…
Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks
Éloïse Benito-Rodriguez, Einar Urdshals, Jasmina Nasufi +1
Understanding Large Language Models (LLMs) is key to ensure their safe and beneficial deployment. This task is complicated by the difficulty of interpretability of LLM structures,…
Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
Einar Urdshals, Edmund Lau, Jesse Hoogland +2
We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through…
Electronic structure of liquid xenon in the context of light dark matter direct detection
Riccardo Catena, Luca Marin, Marek Matas +2
We present a description of the electronic structure of xenon within the density-functional theory formalism with the goal of accurately modeling dark-matter-induced ionisation in…
Structure Development in List-Sorting Transformers
Einar Urdshals, Jasmina Urdshals
We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers. At the end of training, the model organizes its attention…
Dark Matter-induced electron excitations in silicon and germanium with Deep Learning
Riccardo Catena, Einar Urdshals
We train a deep neural network (DNN) to output rates of dark matter (DM) induced electron excitations in silicon and germanium detectors. Our DNN provides a massive speedup of arou…
Direct searches for general dark matter-electron interactions with graphene detectors: Part II. Sensitivity studies
Riccardo Catena, Timon Emken, Marek Matas +2
We use a formalism that describes electron ejections from graphene-like targets by dark matter (DM) scattering for general forms of scalar and spin 1/2 DM-electron interactions in…
Direct searches for general dark matter-electron interactions with graphene detectors: Part I. Electronic structure calculations
Riccardo Catena, Timon Emken, Marek Matas +2
We develop a formalism to describe electron ejections from graphene-like targets by dark matter (DM) scattering for general forms of scalar and spin 1/2 DM-electron interactions an…
Dark matter - electron interactions in materials beyond the dark photon model
Riccardo Catena, Daniel Cole, Timon Emken +4
The search for sub-GeV dark matter (DM) particles via electronic transitions in underground detectors attracted much theoretical and experimental interest in the past few years. A…
Crystal responses to general dark matter-electron interactions
Riccardo Catena, Timon Emken, Marek Matas +2
We develop a formalism to describe the scattering of dark matter (DM) particles by electrons bound in crystals for a general form of the underlying DM-electron interaction. Such a…
On dark atoms, massive dark photons and millicharged sub-components
Felix Kahlhoefer, Einar Urdshals
We present a simple model of two dark matter species with opposite millicharge that can form electrically neutral bound states via the exchange of a massive dark photon. If bound s…