150 citations · 508 across the 11 of their papers we have counts for
11 papers
Attacks on Online Learners: a Teacher-Student Analysis
Riccardo Giuseppe Margiotta, Sebastian Goldt, Guido Sanguinetti
Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions. While a large…
Bayesian reconstruction of memories stored in neural networks from their connectivity
Sebastian Goldt, Florent Krzakala, Lenka Zdeborová +1
The advent of comprehensive synaptic wiring diagrams of large neural circuits has created the field of connectomics and given rise to a number of open research questions. One such…
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed
Maria Refinetti, Sebastian Goldt, Florent Krzakala +1
A recent series of theoretical works showed that the dynamics of neural networks with a certain initialisation are well-captured by kernel methods. Concurrent empirical work demons…
Learning curves of generic features maps for realistic datasets with a teacher-student model
Bruno Loureiro, Cédric Gerbelot, Hugo Cui +4
Teacher-student models provide a framework in which the typical-case performance of high-dimensional supervised learning can be described in closed form. The assumptions of Gaussia…
The Gaussian equivalence of generative models for learning with shallow neural networks
Sebastian Goldt, Bruno Loureiro, Galen Reeves +3
Understanding the impact of data structure on the computational tractability of learning is a key challenge for the theory of neural networks. Many theoretical works do not explici…
Modelling the influence of data structure on learning in neural networks: the hidden manifold model
Sebastian Goldt, Marc Mézard, Florent Krzakala +1
Understanding the reasons for the success of deep neural networks trained using stochastic gradient-based methods is a key open problem for the nascent theory of deep learning. The…
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe +2
Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics…
Generalisation dynamics of online learning in over-parameterised neural networks
Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe +2
Deep neural networks achieve stellar generalisation on a variety of problems, despite often being large enough to easily fit all their training data. Here we study the generalisati…
Thermodynamic efficiency of learning a rule in neural networks
Sebastian Goldt, Udo Seifert
Biological systems have to build models from their sensory data that allow them to efficiently process previously unseen inputs. Here, we study a neural network learning a linearly…
Stochastic Thermodynamics of Learning
Sebastian Goldt, Udo Seifert
Virtually every organism gathers information about its noisy environment and builds models from that data, mostly using neural networks. Here, we use stochastic thermodynamics to a…
Stochastic thermodynamics of resetting
Jaco Fuchs, Sebastian Goldt, Udo Seifert
Stochastic dynamics with random resetting leads to a non-equilibrium steady state. Here, we consider the thermodynamics of resetting by deriving the first and second law for reset…