6 citations · 19 across the 19 of their papers we have counts for
19 papers
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
Abhinav Chakraborty, Subha Maity
Multi-source transfer learning can improve target-domain estimation by leveraging related source data, but its benefits depend on unknown source-to-target biases. This raises a fun…
Limitations of refinement methods for weak to strong generalization
Seamus Somerstep, Ya'acov Ritov, Mikhail Yurochkin +2
Standard techniques for aligning large language models (LLMs) utilize human-produced data, which could limit the capability of any aligned LLM to human level. Label refinement and…
CARROT: A Cost Aware Rate Optimal Router
Seamus Somerstep, Felipe Maia Polo, Allysson Flavio Melo de Oliveira +5
With the rapid growth in the number of Large Language Models (LLMs), there has been a recent interest in LLM routing, or directing queries to the cheapest LLM that can deliver a su…
Microfoundation Inference for Strategic Prediction
Daniele Bracale, Subha Maity, Felipe Maia Polo +3
Often in prediction tasks, the predictive model itself can influence the distribution of the target variable, a phenomenon termed performative prediction. Generally, this influence…
Learning the Distribution Map in Reverse Causal Performative Prediction
Daniele Bracale, Subha Maity, Moulinath Banerjee +1
In numerous predictive scenarios, the predictive model affects the sampling distribution; for example, job applicants often meticulously craft their resumes to navigate through a s…
Aligners: Decoupling LLMs and Alignment
Lilian Ngweta, Mayank Agarwal, Subha Maity +3
Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be r…
Weak Supervision Performance Evaluation via Partial Identification
Felipe Maia Polo, Subha Maity, Mikhail Yurochkin +2
Programmatic Weak Supervision (PWS) enables supervised model training without direct access to ground truth labels, utilizing weak labels from heuristics, crowdsourcing, or pre-tra…
An Investigation of Representation and Allocation Harms in Contrastive Learning
Subha Maity, Mayank Agarwal, Mikhail Yurochkin +1
The effect of underrepresentation on the performance of minority groups is known to be a serious problem in supervised learning settings; however, it has been underexplored so far…
Bayes classifier cannot be learned from noisy responses with unknown noise rates
Soham Bakshi, Subha Maity
Training a classifier with noisy labels typically requires the learner to specify the distribution of label noise, which is often unknown in practice. Although there have been some…
Simple Disentanglement of Style and Content in Visual Representations
Lilian Ngweta, Subha Maity, Alex Gittens +2
Learning visual representations with interpretable features, i.e., disentangled representations, remains a challenging problem. Existing methods demonstrate some success but are ha…
RMExplorer: A Visual Analytics Approach to Explore the Performance and the Fairness of Disease Risk Models on Population Subgroups
Bum Chul Kwon, Uri Kartoun, Shaan Khurshid +7
Disease risk models can identify high-risk patients and help clinicians provide more personalized care. However, risk models developed on one dataset may not generalize across dive…
How does overparametrization affect performance on minority groups?
Subha Maity, Saptarshi Roy, Songkai Xue +2
The benefits of overparameterization for the overall performance of modern machine learning (ML) models are well known. However, the effect of overparameterization at a more granul…
Understanding new tasks through the lens of training data via exponential tilting
Subha Maity, Mikhail Yurochkin, Moulinath Banerjee +1
Deploying machine learning models to new tasks is a major challenge despite the large size of the modern training datasets. However, it is conceivable that the training data can be…
Predictor-corrector algorithms for stochastic optimization under gradual distribution shift
Subha Maity, Debarghya Mukherjee, Moulinath Banerjee +1
Time-varying stochastic optimization problems frequently arise in machine learning practice (e.g. gradual domain shift, object tracking, strategic classification). Although most pr…
A linear adjustment based approach to posterior drift in transfer learning
Subha Maity, Diptavo Dutta, Jonathan Terhorst +2
We present a new model and methods for the posterior drift problem where the regression function in the target domain is modeled as a linear adjustment (on an appropriate scale) of…
Statistical inference for individual fairness
Subha Maity, Songkai Xue, Mikhail Yurochkin +1
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., gende…
Does enforcing fairness mitigate biases caused by subpopulation shift?
Subha Maity, Debarghya Mukherjee, Mikhail Yurochkin +1
Many instances of algorithmic bias are caused by subpopulation shifts. For example, ML models often perform worse on demographic groups that are underrepresented in the training da…
Minimax optimal approaches to the label shift problem in non-parametric settings
Subha Maity, Yuekai Sun, Moulinath Banerjee
We study the minimax rates of the label shift problem in non-parametric classification. In addition to the unsupervised setting in which the learner only has access to unlabeled ex…
Meta-analysis of heterogeneous data: integrative sparse regression in high-dimensions
Subha Maity, Yuekai Sun, Moulinath Banerjee
We consider the task of meta-analysis in high-dimensional settings in which the data sources are similar but non-identical. To borrow strength across such heterogeneous datasets, w…