activity
20142024
most citedStochastic Variational Deep Kernel Learning

102 citations · 141 across the 12 of their papers we have counts for

collaborators

12 papers

cs.LG2024

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion

Hossein Souri, Arpit Bansal, Hamid Kazemi +7

Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can po…

stat.ML20241 cited

Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors

Tim G. J. Rudner, Ya Shi Zhang, Andrew Gordon Wilson +1

Machine learning models often perform poorly under subpopulation shifts in the data distribution. Developing methods that allow machine learning models to better generalize to such…

stat.ML20231 cited

Function-Space Regularization in Neural Networks: A Probabilistic Perspective

Tim G. J. Rudner, Sanyam Kapoor, Shikai Qiu +1

Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it c…

cs.LG20237 cited

A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning

Valeriia Cherepanova, Roman Levin, Gowthami Somepalli +5

Academic tabular benchmarks often contain small sets of curated features. In contrast, data scientists typically collect as many features as possible into their datasets, and even…

cs.LG20232 cited

Fortuna: A Library for Uncertainty Quantification in Deep Learning

Gianluca Detommaso, Alberto Gasparin, Michele Donini +3

We present Fortuna, an open-source library for uncertainty quantification in deep learning. Fortuna supports a range of calibration techniques, such as conformal prediction that ca…

cs.LG2022

Low-Precision Arithmetic for Fast Gaussian Processes

Wesley J. Maddox, Andres Potapczynski, Andrew Gordon Wilson

Low-precision arithmetic has had a transformative effect on the training of neural networks, reducing computation, memory and energy requirements. However, despite its promise, low…