12 citations · 24 across the 18 of their papers we have counts for
10 papers · 1 filter
Compositional Self-Improvement: Promises and Pitfalls
Changho Shin, Daiwei Chen, Brenden Lake +2
Although self-improvement is becoming increasingly important as tasks become more complex, models struggle to generate reliable supervision for harder, out-of-distribution instance…
Almost Asymptotically Optimal Active Clustering Through Pairwise Observations
Rachel S. Y. Teo, P. N. Karthik, Ramya Korlakai Vinayak +1
We propose a new analysis framework for clustering items into an unknown number of distinct groups using noisy and actively collected responses. At each time step, an agent…
Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measure
Zhi Wang, Chicheng Zhang, Ramya Korlakai Vinayak
In lifelong learning, a learner faces a sequence of tasks with shared structure and aims to identify and leverage it to accelerate learning. We study the setting where such structu…
ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
Daisuke Yamada, Harit Vishwakarma, Ramya Korlakai Vinayak
Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment---posing serious risks in safety-critic…
PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences
Daiwei Chen, Yi Chen, Aniket Rege +1
Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically…
Taming False Positives in Out-of-Distribution Detection with Human Feedback
Harit Vishwakarma, Heguang Lin, Ramya Korlakai Vinayak
Robustness to out-of-distribution (OOD) samples is crucial for safely deploying machine learning models in the open world. Recent works have focused on designing scoring functions…
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
Harit Vishwakarma, Reid, Chen +4
Auto-labeling is an important family of techniques that produce labeled training sets with minimum manual labeling. A prominent variant, threshold-based auto-labeling (TBAL), works…
Metric Learning from Limited Pairwise Preference Comparisons
Zhi Wang, Geelon So, Ramya Korlakai Vinayak
We study metric learning from preference comparisons under the ideal point model, in which a user prefers an item over another if it is closer to their latent ideal item. These ite…
Promises and Pitfalls of Threshold-based Auto-labeling
Harit Vishwakarma, Heguang Lin, Frederic Sala +1
Creating large-scale high-quality labeled datasets is a major bottleneck in supervised machine learning workflows. Threshold-based auto-labeling (TBAL), where validation data obtai…
Optimal Estimation of Change in a Population of Parameters
Ramya Korlakai Vinayak, Weihao Kong, Sham M. Kakade
Paired estimation of change in parameters of interest over a population plays a central role in several application domains including those in the social sciences, epidemiology, me…