Statistical Learning
How degenerate is the parametrization of neural networks with the ReLU activation function?
Dennis Maximilian Elbrรคchter, Julius Berner, Philipp Grohs
Neural Information Processing Systems http://nips.cc/
Data-Informed Geometric Space Selection
Geometric representation learning (e.g., hyperbolic and spherical geometry) has proven to be efficacious in solving many intricate machine learning tasks.
Imbalance Trouble: Revisiting Neural-Collapse Geometry
Towards this end, we adoptthe unconstrained-features model (UFM), a recent theoretical model for studying neural collapse, and introduce Simplex-Encoded-Labels Interpolation (SELI) as an invariant characterizationof theneuralcollapsephenomenon.
ae07d152c51ea2ddae65aa7192eb5ff7-Paper-Conference.pdf
Recent work has shown that a much simpler model, simple graph convolution (SGC) (Wu et al., 2019),iscompetitivewithGCNs incommon graph machine learning benchmarks.
A Guide Through the Zoo of Biased SGD
We also provide examples where biased estimators outperform their unbiased counterparts or where unbiased versions are simply not available. Finally, we demonstrate the effectiveness of our framework through experimental results that validate our theoretical findings.