By applying attention and feed-forward networks to inverted variate tokens instead of temporal tokens, iTransformer achieves state-of-the-art performance on real-world time series forecasting datasets.
A regularity and compactness theory for immersed stable minimal hypersurfaces of multiplicity at most 2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We prove that a stable minimal hypersurface of an open ball having a singular set of locally finite codimension 2 Hausdorff measure which is weakly close to a multiplicity 2 hyperplane is a 2-valued C^{1, alpha} graph in the interior. Applications including a compactness theorem for a class of immersed stable minimal hypersurfaces and a pointwise curvature estimate for the hypersurfaces in this class in low dimensions are also discussed.
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
By applying attention and feed-forward networks to inverted variate tokens instead of temporal tokens, iTransformer achieves state-of-the-art performance on real-world time series forecasting datasets.