Search Results for author:
Found 17 papers, 4 papers with code
Leveraging free energy in pretraining model selection for improved fine-tuning
Recent advances in artificial intelligence have been fueled by the development of foundation models such as BERT, GPT, T5, and Vision Transformers.
Pathwise Gradient Variance Reduction with Control Variates in Variational Inference
In this work, we review existing control-variates-based variance reduction methods for pathwise gradient estimators to assess their effectiveness.
Temperature Optimization for Bayesian Deep Learning
The Cold Posterior Effect (CPE) is a phenomenon in Bayesian Deep Learning (BDL), where tempering the posterior to a cold temperature often improves the predictive performance of the posterior predictive distribution (PPD).
The Developmental Landscape of In-Context Learning
We show that in-context learning emerges in transformers in discrete developmental stages, when they are trained on either language modeling or linear regression tasks.
Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
To address this limitation, this paper proposes a framework for achieving causal fairness based on the notion of interventions when the true causal graph is partially known.
Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition
We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theory (SLT).
The Local Learning Coefficient: A Singularity-Aware Complexity Measure
The Local Learning Coefficient (LLC) is introduced as a novel complexity measure for deep neural networks (DNNs).
Technical outlier detection via convolutional variational autoencoder for the ADMANI breast mammogram dataset
The ADMANI datasets (annotated digital mammograms and associated non-image datasets) from the Transforming Breast Cancer Screening with AI programme (BRAIx) run by BreastScreen Victoria in Australia are multi-centre, large scale, clinically curated, real-world databases.
Variational Bayesian Neural Networks via Resolution of Singularities
In this work, we advocate for the importance of singular learning theory (SLT) as it pertains to the theory and practice of variational inference in Bayesian neural networks (BNNs).
Counterfactual Fairness with Partially Known Causal Graph
Interestingly, we find that counterfactual fairness can be achieved as if the true causal graph were fully known, when specific background knowledge is provided: the sensitive attributes do not have ancestors in the causal graph.
Variational Inference via Resolution of Singularities
The approximation relies on a central result from singular learning theory according to which the posterior distribution over the parameters of a singular model, following an algebraic-geometrical transformation known as a desingularization map, is asymptotically a mixture of standard forms.
Deep Learning is Singular, and That's Good
In singular models, the optimal set of parameters forms an analytic set with singularities and classical statistical inference cannot be applied to such models.
The Fairness-Accuracy Pareto Front
Algorithmic fairness seeks to identify and correct sources of bias in machine learning algorithms.
Automating the assessment of biofouling in images using expert agreement as a gold standard
Biofouling is the accumulation of organisms on surfaces immersed in water.
A Shooting Formulation of Deep Learning
Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of an ordinary differential equation (ODE).
The fairness-accuracy landscape of neural classifiers
That machine learning algorithms can demonstrate bias is well-documented by now.
Direction-Projection-Permutation for High Dimensional Hypothesis Tests
Motivated by the prevalence of high dimensional low sample size datasets in modern statistical applications, we propose a general nonparametric framework, Direction-Projection-Permutation (DiProPerm), for testing high dimensional hypotheses.
Methodology
