Search Results for author:
Found 13 papers, 7 papers with code
Aligners: Decoupling LLMs and Alignment
Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications.
Estimating Fréchet bounds for validating programmatic weak supervision
We develop methods for estimating Fr\'echet bounds on (possibly high-dimensional) distribution classes in which some variables are continuous-valued.
An Investigation of Representation and Allocation Harms in Contrastive Learning
In this paper, we demonstrate that contrastive learning (CL), a popular variant of SSL, tends to collapse representations of minority groups with certain majority groups.
Bayes classifier cannot be learned from noisy responses with unknown noise rates
In the special cases in which the Bayes decision rule is identified, we develop a simple algorithm to learn the Bayes decision rule, that does not require knowledge of the noise distribution.
Simple Disentanglement of Style and Content in Visual Representations
Learning visual representations with interpretable features, i. e., disentangled representations, remains a challenging problem.
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.
Predictor-corrector algorithms for stochastic optimization under gradual distribution shift
Time-varying stochastic optimization problems frequently arise in machine learning practice (e. g. gradual domain shift, object tracking, strategic classification).
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.
Does enforcing fairness mitigate biases caused by subpopulation shift?
Many instances of algorithmic bias are caused by subpopulation shifts.
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.
Minimax optimal approaches to the label shift problem in non-parametric settings
We study the minimax rates of the label shift problem in non-parametric classification.
Meta-analysis of heterogeneous data: integrative sparse regression in high-dimensions
We consider the task of meta-analysis in high-dimensional settings in which the data sources are similar but non-identical.
