TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
Warwick Nash, Tracy Sellers, Simon Talbot, Andrew Cawthorn, and Wes Ford
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 6roles
dataset 1polarities
use dataset 1representative citing papers
Neural networks are compressed by lumping neurons with approximately matching dynamics in a polynomial ODE encoding, yielding substantial size reduction with preserved accuracy on synthetic and regression tasks.
Spline encodings for numerical features show task-dependent performance in tabular deep learning, with piecewise-linear encoding robust for classification and variable results for regression depending on spline family, knot strategy, and backbone.
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
ConformaDecompose decomposes conformal prediction uncertainty by progressively localizing calibration sets, revealing reducible epistemic components that align with model limitations across tasks.
Systematic benchmarking reveals that regression calibration metrics frequently disagree on recalibration quality, with ENCE and CWC identified as more consistent performers.
citing papers explorer
-
TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations
TCD-Arena is a new customizable testing framework that runs millions of experiments to map how 33 different assumption violations affect time series causal discovery methods and shows ensembles can boost overall robustness.
-
Neural Network Compression by Approximate Differential Equivalence
Neural networks are compressed by lumping neurons with approximately matching dynamics in a polynomial ODE encoding, yielding substantial size reduction with preserved accuracy on synthetic and regression tasks.
-
From Uniform to Learned Knots: A Study of Spline-Based Numerical Encodings for Tabular Deep Learning
Spline encodings for numerical features show task-dependent performance in tabular deep learning, with piecewise-linear encoding robust for classification and variable results for regression depending on spline family, knot strategy, and backbone.
-
A Composite Activation Function for Learning Stable Binary Representations
HTAF is a sigmoid-tanh composite that approximates the Heaviside function to allow stable gradient training of binary activation networks, yielding ICBMs with stable discretization and competitive performance on image tasks.
-
ConformaDecompose: Explaining Uncertainty via Calibration Localization
ConformaDecompose decomposes conformal prediction uncertainty by progressively localizing calibration sets, revealing reducible epistemic components that align with model limitations across tasks.
-
Evaluating the Quality of the Quantified Uncertainty for (Re)Calibration of Data-Driven Regression Models
Systematic benchmarking reveals that regression calibration metrics frequently disagree on recalibration quality, with ENCE and CWC identified as more consistent performers.