7 papers
The price of multi-group transductive learning
Noah Bergam, Samuel Deng, Daniel Hsu
We show every multi-group learner in the leave-one-out transductive setting may incur a surprisingly large multiplicative penalty in its error rate on some group relative to the er…
A One-Inclusion Graph Approach to Multi-Group Learning
Noah Bergam, Samuel Deng, Daniel Hsu
We prove the tightest-known upper bounds on the sample complexity of multi-group learning. Our algorithm extends the one-inclusion graph prediction strategy using a generalization…
t-SNE Exaggerates Clusters, Provably
Noah Bergam, Szymon Snoeck, Nakul Verma
Central to the widespread use of t-distributed stochastic neighbor embedding (t-SNE) is the conviction that it produces visualizations whose structure roughly matches that of the i…
Compressibility Barriers to Neighborhood-Preserving Data Visualizations
Szymon Snoeck, Noah Bergam, Nakul Verma
To what extent is it possible to visualize high-dimensional data in two- or three-dimensional plots? We reframe this question in terms of embedding -vertex graphs (representing…
ClusterSC: Advancing Synthetic Control with Donor Selection
Saeyoung Rho, Andrew Tang, Noah Bergam +2
In causal inference with observational studies, synthetic control (SC) has emerged as a prominent tool. SC has traditionally been applied to aggregate-level datasets, but more rece…
Confidence-Calibrated Ensemble Dense Phrase Retrieval
William Yang, Noah Bergam, Arnav Jain +1
In this paper, we consider the extent to which the transformer-based Dense Passage Retrieval (DPR) algorithm, developed by (Karpukhin et. al. 2020), can be optimized without furthe…
Legal and Political Stance Detection of SCOTUS Language
Noah Bergam, Emily Allaway, Kathleen McKeown
We analyze publicly available US Supreme Court documents using automated stance detection. In the first phase of our work, we investigate the extent to which the Court's public-fac…