Search Results for author:
Found 48 papers, 24 papers with code
Two Simple Ways to Learn Individual Fairness Metric from Data
Individual fairness was proposed to address some of the shortcomings of group fairness.
Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness
While several toolkits exist to aid machine learning practitioners in addressing fairness issues, little is known about the strategies practitioners employ to evaluate model fairness and what factors influence their assessment, particularly in the context of text classification.
Simple Disentanglement of Style and Content in Visual Representations
Learning visual representations with interpretable features, i. e., disentangled representations, remains a challenging problem.
Calibrated Data-Dependent Constraints with Exact Satisfaction Guarantees
We consider the task of training machine learning models with data-dependent constraints.
Sampling with Mollified Interaction Energy Descent
These energies rely on mollifier functions -- smooth approximations of the Dirac delta originated from PDE theory.
Outlier-Robust Group Inference via Gradient Space Clustering
Traditional machine learning models focus on achieving good performance on the overall training distribution, but they often underperform on minority groups.
How does overparametrization affect performance on minority groups?
The benefits of overparameterization for the overall performance of modern machine learning (ML) models are well known.
Understanding new tasks through the lens of training data via exponential tilting
However, it is conceivable that the training data can be reweighted to be more representative of the new (target) task.
Domain Adaptation meets Individual Fairness. And they get along
In this paper, we leverage this connection between algorithmic fairness and distribution shifts to show that algorithmic fairness interventions can help ML models overcome distribution shifts, and that domain adaptation methods (for overcoming distribution shifts) can mitigate algorithmic biases.
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
We use manifold learning to compare the intrinsic geometric structures of different datasets by comparing their diffusion operators, symmetric positive-definite (SPD) matrices that relate to approximations of the continuous Laplace-Beltrami operator from discrete samples.
Rewiring with Positional Encodings for Graph Neural Networks
As a conservative alternative, we use positional encodings to expand receptive fields to $r$-hop neighborhoods.
Learning Proximal Operators to Discover Multiple Optima
We present an end-to-end method to learn the proximal operator of a family of training problems so that multiple local minima can be quickly obtained from initial guesses by iterating the learned operator, emulating the proximal-point algorithm that has fast convergence.
On sensitivity of meta-learning to support data
Meta-learning algorithms are widely used for few-shot learning.
Post-processing for Individual Fairness
In this work, we propose general post-processing algorithms for individual fairness (IF).
$k$-Mixup Regularization for Deep Learning via Optimal Transport
To better leverage the structure of the data, we extend mixup to $k$-mixup by perturbing $k$-batches of training points in the direction of other $k$-batches using displacement interpolation, i. e. interpolation under the Wasserstein metric.
Propagating Distributions through Neural Networks
We propose a new approach to propagating probability distributions through neural networks.
Your fairness may vary: Pretrained language model fairness in toxic text classification
Through the analysis of more than a dozen pretrained language models of varying sizes on two toxic text classification tasks (English), we demonstrate that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics.
Measuring the robustness of Gaussian processes to kernel choice
We demonstrate in both synthetic and real-world examples that decisions made with a GP can exhibit non-robustness to kernel choice, even when prior draws are qualitatively interchangeable to a user.
k-Mixup Regularization for Deep Learning via Optimal Transport
Mixup is a popular regularization technique for training deep neural networks that can improve generalization and increase adversarial robustness.
Individually Fair Gradient Boosting
Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern.
Statistical inference for individual fairness
As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e. g., gender and racial biases) has come to the fore of the public's attention.
Individually Fair Ranking
We develop an algorithm to train individually fair learning-to-rank (LTR) models.
Individually Fair Rankings
We develop an algorithm to train individually fair learning-to-rank (LTR) models.
Outlier Robust Optimal Transport
In light of recent advances in solving the OT problem, OT distances are widely used as loss functions in minimum distance estimation.
Does enforcing fairness mitigate biases caused by subpopulation shift?
Many instances of algorithmic bias are caused by subpopulation shifts.
Online Semi-Supervised Learning with Bandit Feedback
We formulate a new problem at the intersectionof semi-supervised learning and contextual bandits, motivated by several applications including clini-cal trials and ad recommendations.
There is no trade-off: enforcing fairness can improve accuracy
If the algorithmic biases in an ML model are due to sampling biases in the training data, then enforcing algorithmic fairness may improve the performance of the ML model on unbiased test data.
Continuous Regularized Wasserstein Barycenters
Leveraging a new dual formulation for the regularized Wasserstein barycenter problem, we introduce a stochastic algorithm that constructs a continuous approximation of the barycenter.
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
Model Fusion with Kullback--Leibler Divergence
Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors and proceeds using a simple assign-and-average approach.
SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
In this paper, we cast fair machine learning as invariant machine learning.
Two Simple Ways to Learn Individual Fairness Metrics from Data
Individual fairness is an intuitive definition of algorithmic fairness that addresses some of the drawbacks of group fairness.
Auditing ML Models for Individual Bias and Unfairness
We consider the task of auditing ML models for individual bias/unfairness.
Federated Learning with Matched Averaging
Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud.
Alleviating Label Switching with Optimal Transport
Label switching is a phenomenon arising in mixture model posterior inference that prevents one from meaningfully assessing posterior statistics using standard Monte Carlo procedures.
Statistical Model Aggregation via Parameter Matching
We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets.
On Efficient Multilevel Clustering via Wasserstein Distances
We propose a novel approach to the problem of multilevel clustering, which aims to simultaneously partition data in each group and discover grouping patterns among groups in a potentially large hierarchically structured corpus of data.
Training individually fair ML models with Sensitive Subspace Robustness
We consider training machine learning models that are fair in the sense that their performance is invariant under certain sensitive perturbations to the inputs.
Hierarchical Optimal Transport for Document Representation
The ability to measure similarity between documents enables intelligent summarization and analysis of large corpora.
Bayesian Nonparametric Federated Learning of Neural Networks
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.
Dirichlet Simplex Nest and Geometric Inference
We propose Dirichlet Simplex Nest, a class of probabilistic models suitable for a variety of data types, and develop fast and provably accurate inference algorithms by accounting for the model's convex geometry and low dimensional simplicial structure.
Probabilistic Federated Neural Matching
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.
Scalable inference of topic evolution via models for latent geometric structures
We develop new models and algorithms for learning the temporal dynamics of the topic polytopes and related geometric objects that arise in topic model based inference.
UPS: optimizing Undirected Positive Sparse graph for neural graph filtering
In this work we propose a novel approach for learning graph representation of the data using gradients obtained via backpropagation.
Conic Scan-and-Cover algorithms for nonparametric topic modeling
We propose new algorithms for topic modeling when the number of topics is unknown.
Multi-way Interacting Regression via Factorization Machines
We propose a Bayesian regression method that accounts for multi-way interactions of arbitrary orders among the predictor variables.
Multilevel Clustering via Wasserstein Means
We propose a novel approach to the problem of multilevel clustering, which aims to simultaneously partition data in each group and discover grouping patterns among groups in a potentially large hierarchically structured corpus of data.
Geometric Dirichlet Means algorithm for topic inference
We propose a geometric algorithm for topic learning and inference that is built on the convex geometry of topics arising from the Latent Dirichlet Allocation (LDA) model and its nonparametric extensions.
