research
∙
07/11/2023
Weisfeiler and Lehman Go Measurement Modeling: Probing the Validity of the WL Test
The expressive power of graph neural networks is usually measured by com...
share
research
∙
12/13/2022
Simplicity Bias Leads to Amplified Performance Disparities
The simple idea that not all things are equally difficult has surprising...
research
∙
07/20/2022
Measuring and signing fairness as performance under multiple stakeholder distributions
As learning machines increase their influence on decisions concerning hu...
research
∙
03/28/2022
Understanding out-of-distribution accuracies through quantifying difficulty of test samples
Existing works show that although modern neural networks achieve remarka...
research
∙
02/16/2022
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
Discriminative self-supervised learning allows training models on any ra...
research
∙
02/15/2022
Fairness Indicators for Systematic Assessments of Visual Feature Extractors
Does everyone equally benefit from computer vision systems? Answers to t...
research
∙
06/10/2021
Transformed CNNs: recasting pre-trained convolutional layers with self-attention
Vision Transformers (ViT) have recently emerged as a powerful alternativ...
research
∙
03/19/2021
ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases
Convolutional architectures have proven extremely successful for vision ...
research
∙
03/09/2021
More data or more parameters? Investigating the effect of data structure on generalization
One of the central features of deep learning is the generalization abili...
research
∙
06/05/2020
Triple descent and the two kinds of overfitting: Where why do they appear?
A recent line of research has highlighted the existence of a double desc...
research
∙
11/29/2019
On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks
The gradient noise (GN) in the stochastic gradient descent (SGD) algorit...
research
∙
06/16/2019
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
Despite the phenomenal success of deep neural networks in a broad range ...
research
∙
01/18/2019
A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
The gradient noise (GN) in the stochastic gradient descent (SGD) algorit...
research
∙
01/06/2019
Scaling description of generalization with number of parameters in deep learning
We provide a description for the evolution of the generalization perform...
research
∙
10/22/2018
A jamming transition from under- to over-parametrization affects loss landscape and generalization
We argue that in fully-connected networks a phase transition delimits th...
research
∙
09/25/2018
The jamming transition as a paradigm to understand the loss landscape of deep neural networks
Deep learning has been immensely successful at a variety of tasks, rangi...
research
∙
04/18/2017
SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
We publicly release a new large-scale dataset, called SearchQA, for mach...
research
∙
03/23/2017
Perspective: Energy Landscapes for Machine Learning
Machine learning techniques are being increasingly used as flexible non-...
research
∙
11/22/2016
Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond
We look at the eigenvalues of the Hessian of a loss function before and ...
research
∙
11/06/2016
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
This paper proposes a new optimization algorithm called Entropy-SGD for ...
research
∙
11/19/2015
Universal halting times in optimization and machine learning
The authors present empirical distributions for the halting time (measur...
research
∙
12/20/2014