Sebastian Goldt

46 papers A* 14A 1Journal 28Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A theory of learning data statistics in diffusion models, from easy to hard. CoRR Lorenzo Bardone, Claudia Merger, Sebastian Goldt
2025	J	`jnl`	Exploring the potential of Direct Feedback Alignment for Continual Learning. Trans. Mach. Learn. Res. Sara Folchini, Viplove Arora, Sebastian Goldt
2025	A*	`conf`	Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions. ICML Fabiola Ricci, Lorenzo Bardone, Sebastian Goldt
2025	J	`jnl`	Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions. CoRR Fabiola Ricci, Lorenzo Bardone, Sebastian Goldt
2025	J	`jnl`	Generalization Dynamics of Linear Diffusion Models. CoRR Claudia Merger, Sebastian Goldt
2025	—	`conf`	How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks. CPAL William T. Redman, Zhangyang Wang, Alessandro Ingrosso, Sebastian Goldt
2025	J	`jnl`	Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation. CoRR Alessio Giorlandino, Sebastian Goldt
2024	A*	`conf`	A distributional simplicity bias in the learning dynamics of transformers. NeurIPS Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
2024	J	`jnl`	A distributional simplicity bias in the learning dynamics of transformers. CoRR Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
2024	A*	`conf`	Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks. NeurIPS Eszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt
2024	J	`jnl`	On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks. CoRR William T. Redman, Zhangyang Wang, Alessandro Ingrosso, Sebastian Goldt
2024	A*	`conf`	Sliding Down the Stairs: How Correlated Latent Variables Accelerate Learning with Neural Networks. ICML Lorenzo Bardone, Sebastian Goldt
2024	J	`jnl`	Sliding down the stairs: how correlated latent variables accelerate learning with neural networks. CoRR Lorenzo Bardone, Sebastian Goldt
2024	J	`jnl`	The impact of memory on learning sequence-to-sequence tasks. Mach. Learn. Sci. Technol. Alireza Seif, Sarah A. M. Loos, Gennaro Tucci, Édgar Roldán, Sebastian Goldt
2023	A*	`conf`	Attacks on Online Learners: a Teacher-Student Analysis. NeurIPS Riccardo Giuseppe Margiotta, Sebastian Goldt, Guido Sanguinetti
2023	J	`jnl`	Attacks on Online Learners: a Teacher-Student Analysis. CoRR Riccardo Giuseppe Margiotta, Sebastian Goldt, Guido Sanguinetti
2023	J	`jnl`	Bayesian reconstruction of memories stored in neural networks from their connectivity. PLoS Comput. Biol. Sebastian Goldt, Florent Krzakala, Lenka Zdeborová, Nicolas Brunel
2023	J	`jnl`	Learning from higher-order statistics, efficiently: hypothesis tests, random features, and neural networks. CoRR Eszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt
2023	A*	`conf`	Neural networks trained with SGD learn distributions of increasing complexity. ICML Maria Refinetti, Alessandro Ingrosso, Sebastian Goldt
2023	J	`jnl`	Optimal inference of a generalised Potts model by single-layer transformers with factored attention. CoRR Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
2023	A	`conf`	Quantifying lottery tickets under label noise: accuracy, calibration, and complexity. UAI Viplove Arora, Daniele Irto, Sebastian Goldt, Guido Sanguinetti
2023	J	`jnl`	Quantifying lottery tickets under label noise: accuracy, calibration, and complexity. CoRR Viplove Arora, Daniele Irto, Sebastian Goldt, Guido Sanguinetti
2023	J	`jnl`	The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions. CoRR Nishil Patel, Sebastian Lee, Stefano Sarao Mannelli, Sebastian Goldt, Andrew M. Saxe
2022	J	`jnl`	Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation. CoRR Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe
2022	A*	`conf`	Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation. ICML Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe
2022	J	`jnl`	Neural networks trained with SGD learn distributions of increasing complexity. CoRR Maria Refinetti, Alessandro Ingrosso, Sebastian Goldt
2022	A*	`conf`	Redundant representations help generalization in wide neural networks. NeurIPS Diego Doimo, Aldo Glielmo, Sebastian Goldt, Alessandro Laio
2022	A*	`conf`	The dynamics of representation learning in shallow, non-linear autoencoders. ICML Maria Refinetti, Sebastian Goldt
2022	J	`jnl`	The dynamics of representation learning in shallow, non-linear autoencoders. CoRR Maria Refinetti, Sebastian Goldt
2022	J	`jnl`	The impact of memory on learning sequence-to-sequence tasks. CoRR Alireza Seif, Sarah A. M. Loos, Gennaro Tucci, Édgar Roldán, Sebastian Goldt
2021	A*	`conf`	Align, then memorise: the dynamics of learning with feedback alignment. ICML Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt
2021	J	`jnl`	Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model. CoRR Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2021	A*	`conf`	Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed. ICML Maria Refinetti, Sebastian Goldt, Florent Krzakala, Lenka Zdeborová
2021	J	`jnl`	Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed. CoRR Maria Refinetti, Sebastian Goldt, Florent Krzakala, Lenka Zdeborová
2021	A*	`conf`	Continual Learning in the Teacher-Student Setup: Impact of Task Similarity. ICML Sebastian Lee, Sebastian Goldt, Andrew M. Saxe
2021	J	`jnl`	Continual Learning in the Teacher-Student Setup: Impact of Task Similarity. CoRR Sebastian Lee, Sebastian Goldt, Andrew M. Saxe
2021	A*	`conf`	Learning curves of generic features maps for realistic datasets with a teacher-student model. NeurIPS Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2021	J	`jnl`	Representation mitosis in wide neural networks. CoRR Diego Doimo, Aldo Glielmo, Sebastian Goldt, Alessandro Laio
2021	—	`conf`	The Gaussian equivalence of generative models for learning with shallow neural networks. MSML Sebastian Goldt, Bruno Loureiro, Galen Reeves, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2020	J	`jnl`	The Gaussian equivalence of generative models for learning with two-layer neural networks. CoRR Sebastian Goldt, Galen Reeves, Marc Mézard, Florent Krzakala, Lenka Zdeborová
2020	J	`jnl`	The dynamics of learning with feedback alignment. CoRR Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt
2019	A*	`conf`	Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. NeurIPS Sebastian Goldt, Madhu Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová
2019	J	`jnl`	Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. CoRR Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová
2019	J	`jnl`	Generalisation dynamics of online learning in over-parameterised neural networks. CoRR Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová
2019	J	`jnl`	Modelling the influence of data structure on learning in neural networks. CoRR Sebastian Goldt, Marc Mézard, Florent Krzakala, Lenka Zdeborová
2018	—	`—`	Stochastic thermodynamics of learning. Sebastian Goldt