Berfin Simsek

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 16

Top Topics

Stationary Points

Multilayer Perceptron

Teacher Student

Top Venues

Publications

Zhengqing Wu, Berfin Simsek, François Ged
The Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escaping, and Network Embedding. CoRR (2024)
Vivien Cabannes, Berfin Simsek, Alberto Bietti
Learning Associative Memories with Gradient Descent. CoRR (2024)
Flavio Martinelli, Berfin Simsek, Johanni Brea, Wulfram Gerstner
Expand-and-Cluster: Exact Parameter Recovery of Neural Networks. CoRR (2023)
Berfin Simsek, Amire Bendjeddou, Wulfram Gerstner, Johanni Brea
Should Under-parameterized Student Networks Copy or Average Teacher Weights? CoRR (2023)
Johanni Brea, Flavio Martinelli, Berfin Simsek, Wulfram Gerstner
MLPGradientFlow: going with the flow of multilayer perceptrons (and finding minima fast and accurately). CoRR (2023)
Berfin Simsek, Amire Bendjeddou, Wulfram Gerstner, Johanni Brea
Should Under-parameterized Student Networks Copy or Average Teacher Weights? NeurIPS (2023)
Berfin Simsek, Melissa Hall, Levent Sagun
Understanding out-of-distribution accuracies through quantifying difficulty of test samples. CoRR (2022)
Arthur Jacot, François Ged, Franck Gabriel, Berfin Simsek, Clément Hongler
Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization. CoRR (2021)
Berfin Simsek, François Ged, Arthur Jacot, Francesco Spadaro, Clément Hongler, Wulfram Gerstner, Johanni Brea
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances. CoRR (2021)
Berfin Simsek, François Ged, Arthur Jacot, Francesco Spadaro, Clément Hongler, Wulfram Gerstner, Johanni Brea
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances. ICML (2021)
Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
Implicit Regularization of Random Feature Models. CoRR (2020)
Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
Implicit Regularization of Random Feature Models. ICML (2020)
Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
Kernel Alignment Risk Estimator: Risk Prediction from Training Data. CoRR (2020)
Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
Kernel Alignment Risk Estimator: Risk Prediction from Training Data. NeurIPS (2020)
Johanni Brea, Berfin Simsek, Bernd Illing, Wulfram Gerstner
Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape. CoRR (2019)
Berfin Simsek, Alper T. Erdogan
Online Bounded Component Analysis: A Simple Recurrent Neural Network with Local Update Rule for Unsupervised Separation of Dependent and Independent Sources. ACSSC (2019)