57 citations · 96 across the 12 of their papers we have counts for
6 papers · 1 filter
Memory Efficient Tabular Foundation Models
Shuting Luo, Monika Mikhail Kanaan, Cameron Gordon +2
Tabular Foundation Models, such as TabPFN, have received a large amount of recent attention due to their performance on in-context tabular machine learning tasks, which often excee…
BOND: License to Train with Black-Box Functions
Andrew Clark, Jack Moursounidis, Osmaan Rasouli +3
We introduce Bounded Numerical Differentiation (BOND), a perturbative method for estimating the gradients of black-box functions. BOND is distinguished by its formulation, which ad…
FeatureCuts: Feature Selection for Large Data by Optimizing the Cutoff
Andy Hu, Devika Prasad, Luiz Pizzato +5
In machine learning, the process of feature selection involves finding a reduced subset of features that captures most of the information required to train an accurate and efficien…
Learning Adapter Rank via Symmetry Breaking
Cooper Doyle, Andy Hu, Rebecca Chan +1
Low-rank adaptation is effective partly because downstream updates lie in a low-dimensional subspace, but the latent rank coordinates of LoRA are not identifiable: any invertible r…
Combining Static and Dynamic Features for Multivariate Sequence Classification
Anna Leontjeva, Ilya Kuzovkin
Model precision in a classification task is highly dependent on the feature space that is used to train the model. Moreover, whether the features are sequential or static will dict…
Temporal Stability in Predictive Process Monitoring
Irene Teinemaa, Marlon Dumas, Anna Leontjeva +1
Predictive process monitoring is concerned with the analysis of events produced during the execution of a business process in order to predict as early as possible the final outcom…