118 citations · 363 across the 33 of their papers we have counts for
11 papers · 1 filter
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
Ibrahim Alabdulmohsin, Xiao Wang, Andreas Steiner +3
We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffir…
Layer-Stack Temperature Scaling
Amr Khalifa, Michael C. Mozer, Hanie Sedghi +2
Recent works demonstrate that early layers in a neural network contain useful information for prediction. Inspired by this, we show that extending temperature scaling across all la…
Revisiting Neural Scaling Laws in Language and Vision
Ibrahim Alabdulmohsin, Behnam Neyshabur, Xiaohua Zhai
The remarkable progress in deep learning in recent years is largely driven by improvements in scale, where bigger models are trained on larger datasets for longer schedules. To pre…
A Reduction to Binary Approach for Debiasing Multiclass Datasets
Ibrahim Alabdulmohsin, Jessica Schrouff, Oluwasanmi Koyejo
We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a seque…
Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
Jessica Schrouff, Natalie Harris, Oluwasanmi Koyejo +14
Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings. Importantl…
The Impact of Reinitialization on Generalization in Convolutional Neural Networks
Ibrahim Alabdulmohsin, Hartmut Maennel, Daniel Keysers
Recent results suggest that reinitializing a subset of the parameters of a neural network during training can improve generalization, particularly for small training sets. We study…
A Generalized Lottery Ticket Hypothesis
Ibrahim Alabdulmohsin, Larisa Markeeva, Daniel Keysers +1
We introduce a generalization to the lottery ticket hypothesis in which the notion of "sparsity" is relaxed by choosing an arbitrary basis in the space of parameters. We present ev…
A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models
Ibrahim Alabdulmohsin, Mario Lucic
We present a scalable post-processing algorithm for debiasing trained models, including deep neural networks (DNNs), which we prove to be near-optimal by bounding its excess Bayes…
Fair Classification via Unconstrained Optimization
Ibrahim Alabdulmohsin
Achieving the Bayes optimal binary classification rule subject to group fairness constraints is known to be reducible, in some cases, to learning a group-wise thresholding rule ove…
Uniform Generalization, Concentration, and Adaptive Learning
Ibrahim Alabdulmohsin
One fundamental goal in any learning algorithm is to mitigate its risk for overfitting. Mathematically, this requires that the learning algorithm enjoys a small generalization risk…
A Mathematical Theory of Learning
Ibrahim Alabdulmohsin
In this paper, a mathematical theory of learning is proposed that has many parallels with information theory. We consider Vapnik's General Setting of Learning in which the learning…