Berfin Simsek - RankMe

22 papers A* 7A 1Misc 1Journal 13

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Flat Channels to Infinity in Neural Loss Landscapes. CoRR Flavio Martinelli, Alexander van Meegen, Berfin Simsek, Wulfram Gerstner, Johanni Brea
2025	A	`conf`	Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence. AISTATS Berfin Simsek, Amire Bendjeddou, Daniel Hsu
2025	A*	`conf`	Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escape, and Network Embedding. ICLR Zhengqing Wu, Berfin Simsek, François Gaston Ged
2024	A*	`conf`	Expand-and-Cluster: Parameter Recovery of Neural Networks. ICML Flavio Martinelli, Berfin Simsek, Wulfram Gerstner, Johanni Brea
2024	A*	`conf`	Learning Associative Memories with Gradient Descent. ICML Vivien Cabannes, Berfin Simsek, Alberto Bietti
2024	J	`jnl`	Learning Associative Memories with Gradient Descent. CoRR Vivien Cabannes, Berfin Simsek, Alberto Bietti
2024	J	`jnl`	Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence. CoRR Berfin Simsek, Amire Bendjeddou, Daniel Hsu
2024	J	`jnl`	The Loss Landscape of Shallow ReLU-like Neural Networks: Stationary Points, Saddle Escaping, and Network Embedding. CoRR Zhengqing Wu, Berfin Simsek, François Ged
2023	J	`jnl`	Expand-and-Cluster: Exact Parameter Recovery of Neural Networks. CoRR Flavio Martinelli, Berfin Simsek, Johanni Brea, Wulfram Gerstner
2023	J	`jnl`	MLPGradientFlow: going with the flow of multilayer perceptrons (and finding minima fast and accurately). CoRR Johanni Brea, Flavio Martinelli, Berfin Simsek, Wulfram Gerstner
2023	A*	`conf`	Should Under-parameterized Student Networks Copy or Average Teacher Weights? NeurIPS Berfin Simsek, Amire Bendjeddou, Wulfram Gerstner, Johanni Brea
2023	J	`jnl`	Should Under-parameterized Student Networks Copy or Average Teacher Weights? CoRR Berfin Simsek, Amire Bendjeddou, Wulfram Gerstner, Johanni Brea
2022	J	`jnl`	Understanding out-of-distribution accuracies through quantifying difficulty of test samples. CoRR Berfin Simsek, Melissa Hall, Levent Sagun
2021	J	`jnl`	Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization. CoRR Arthur Jacot, François Ged, Franck Gabriel, Berfin Simsek, Clément Hongler
2021	A*	`conf`	Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances. ICML Berfin Simsek, François Ged, Arthur Jacot, Francesco Spadaro, Clément Hongler, Wulfram Gerstner, Johanni Brea
2021	J	`jnl`	Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances. CoRR Berfin Simsek, François Ged, Arthur Jacot, Francesco Spadaro, Clément Hongler, Wulfram Gerstner, Johanni Brea
2020	A*	`conf`	Implicit Regularization of Random Feature Models. ICML Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
2020	J	`jnl`	Implicit Regularization of Random Feature Models. CoRR Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
2020	A*	`conf`	Kernel Alignment Risk Estimator: Risk Prediction from Training Data. NeurIPS Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
2020	J	`jnl`	Kernel Alignment Risk Estimator: Risk Prediction from Training Data. CoRR Arthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler, Franck Gabriel
2019	Misc	`conf`	Online Bounded Component Analysis: A Simple Recurrent Neural Network with Local Update Rule for Unsupervised Separation of Dependent and Independent Sources. ACSSC Berfin Simsek, Alper T. Erdogan
2019	J	`jnl`	Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape. CoRR Johanni Brea, Berfin Simsek, Bernd Illing, Wulfram Gerstner