Picture for Berfin Şimşek

Berfin Şimşek

Should Under-parameterized Student Networks Copy or Average Teacher Weights?

Add code
Nov 03, 2023
Viaarxiv icon

Statistical physics, Bayesian inference and neural information processing

Add code
Sep 29, 2023
Figure 1 for Statistical physics, Bayesian inference and neural information processing
Figure 2 for Statistical physics, Bayesian inference and neural information processing
Figure 3 for Statistical physics, Bayesian inference and neural information processing
Figure 4 for Statistical physics, Bayesian inference and neural information processing
Viaarxiv icon

MLPGradientFlow: going with the flow of multilayer perceptrons (and finding minima fast and accurately)

Add code
Jan 25, 2023
Viaarxiv icon

Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization

Add code
Jun 30, 2021
Figure 1 for Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization
Figure 2 for Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization
Figure 3 for Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization
Figure 4 for Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization
Viaarxiv icon

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Add code
May 25, 2021
Figure 1 for Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Figure 2 for Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Figure 3 for Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Figure 4 for Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Viaarxiv icon

Kernel Alignment Risk Estimator: Risk Prediction from Training Data

Add code
Jun 17, 2020
Figure 1 for Kernel Alignment Risk Estimator: Risk Prediction from Training Data
Figure 2 for Kernel Alignment Risk Estimator: Risk Prediction from Training Data
Figure 3 for Kernel Alignment Risk Estimator: Risk Prediction from Training Data
Figure 4 for Kernel Alignment Risk Estimator: Risk Prediction from Training Data
Viaarxiv icon

Implicit Regularization of Random Feature Models

Add code
Feb 19, 2020
Figure 1 for Implicit Regularization of Random Feature Models
Figure 2 for Implicit Regularization of Random Feature Models
Figure 3 for Implicit Regularization of Random Feature Models
Figure 4 for Implicit Regularization of Random Feature Models
Viaarxiv icon