Europe
Alternating optimization of decision trees, with application to learning sparse oblique trees
Miguel A. Carreira-Perpinan, Pooya Tavallali
Thismakesinferenceveryfast,andmaynot even need to use all input featuresto make a prediction (with axis-aligned trees).
Sample Efficient Active Learning of Causal Trees
Kristjan Greenewald, Dmitriy Katz, Karthikeyan Shanmugam, Sara Magliacane, Murat Kocaoglu, Enric Boix Adsera, Guy Bresler
Neural Information Processing Systems http://nips.cc/
Wasserstein convergence of ˇ Cech persistence diagrams for samplings of submanifolds
A multiset is a set where each element appears with some non-zero multiplicity.
On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data
In disciplines such as chemistry, physics, and network science, graphs are a convenient and well-studied mathematical object to represent such interacting entities and their attributes.
AQuantitativeGeometricApproachto Neural-NetworkSmoothness
The techniques for theℓ2-perturbation do not easily transfer to theℓ -case (Leino et al., 2021). One critical step is to measure the Lipschitz constant more precisely and efficiently.
AQuantitativeGeometricApproachto Neural-NetworkSmoothness
The techniques for theℓ2-perturbation do not easily transfer to theℓ -case (Leino et al., 2021). One critical step is to measure the Lipschitz constant more precisely and efficiently.
MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI T obit Klug 1, Kun Wang 1, Stefan Ruschke
In this paper, we propose MotionTTT a deep learning-based test-time-training (TTT) method for accurate motion estimation.
Neural Code Comprehension: A Learnable Representation of Code Semantics
Tal Ben-Nun, Alice Shoshana Jakobovits, Torsten Hoefler
Neural Information Processing Systems http://nips.cc/
Paraphrase Generation with Latent Bag of Words
Yao Fu, Yansong Feng, John P. Cunningham
Neural Information Processing Systems http://nips.cc/
Abstraction based Output Range Analysis for Neural Networks
Pavithra Prabhakar, Zahra Rahimi Afzal
We reduce the output range analysis on theINNs to solving a mixed integer linear programming problem.