Pascal Mattia Esser

According to our database, Pascal Mattia Esser authored at least 10 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?

Gautham Govind Anil, Pascal Mattia Esser, Debarghya Ghoshdastidar

CoRR, 2024

Non-parametric Representation Learning with Kernels.

Pascal Mattia Esser, Maximilian Fleissner, Debarghya Ghoshdastidar

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Representation Learning Dynamics of Self-Supervised Models.

Pascal Mattia Esser, Satyaki Mukherjee, Debarghya Ghoshdastidar

CoRR, 2023

Improved Representation Learning Through Tensorized Autoencoders.

Pascal Mattia Esser, Satyaki Mukherjee, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Representation Power of Graph Convolutions : Neural Tangent Kernel Analysis.

Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar

CoRR, 2022

On the Influence of Enforcing Model Identifiability on Learning dynamics of Gaussian Mixture Models.

Pascal Mattia Esser, Frank Nielsen

CoRR, 2022

2021

Towards Modeling and Resolving Singular Parameter Spaces using Stratifolds.

Pascal Mattia Esser, Frank Nielsen

CoRR, 2021

New Insights into Graph Convolutional Networks using Neural Tangent Kernels.

Mahalakshmi Sabanayagam, Pascal Mattia Esser, Debarghya Ghoshdastidar

CoRR, 2021

Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks.

Pascal Mattia Esser, Leena C. Vankadara, Debarghya Ghoshdastidar

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Near-Optimal Comparison Based Clustering.

Michaël Perrot, Pascal Mattia Esser, Debarghya Ghoshdastidar

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020