4 papers
Metric-Aware PCA as a Linear Instance of Geometric Deep Learning
Michael Leznik
Geometric deep learning organises neural architectures around the symmetries of their data domain, with the choice of symmetry group serving as a geometric prior that determines wh…
Metric-Aware Principal Component Analysis (MAPCA):A Unified Framework for Scale-Invariant Representation Learning
Michael Leznik
We introduce Metric-Aware Principal Component Analysis (MAPCA), a unified framework for scale-invariant representation learning based on the generalised eigenproblem max Tr(W^T Sig…
Soft Mean Expected Calibration Error (SMECE): A Calibration Metric for Probabilistic Labels
Michael Leznik
The Expected Calibration Error (ece), the dominant calibration metric in machine learning, compares predicted probabilities against empirical frequencies of binary outcomes. This i…
The Temporal Markov Transition Field
Michael Leznik
The Markov Transition Field (MTF), introduced by Wang and Oates (2015), encodes a time series as a two-dimensional image by mapping each pair of time steps to the transition probab…