Search Results for author:
Found 7 papers, 2 papers with code
The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization
To reach high performance with deep learning, hyperparameter optimization (HPO) is essential.
A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance
Plotting a learner's generalization performance against the training set size results in a so-called learning curve.
The Shape of Learning Curves: a Review
This important tool can be used for model selection, to predict the effect of more training data, and to reduce the computational complexity of model training and hyperparameter tuning.
A Brief Prehistory of Double Descent
In their thought-provoking paper [1], Belkin et al. illustrate and discuss the shape of risk curves in the context of modern high-complexity learners.
How to Manipulate CNNs to Make Them Lie: the GradCAM Case
This illustrates that GradCAM cannot explain the decision of every CNN and provides a proof of concept showing that it is possible to obfuscate the inner workings of a CNN.
Minimizers of the Empirical Risk and Risk Monotonicity
Plotting a learner's average performance against the number of training samples results in a learning curve.
A Distribution Dependent and Independent Complexity Analysis of Manifold Regularization
Here, we derive sample complexity bounds based on pseudo-dimension for models that add a convex data dependent regularization term to a supervised learning process, as is in particular done in Manifold regularization.
