97 citations · 226 across the 9 of their papers we have counts for
13 papers · 1 filter
Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
Neel Guha, Mayee F. Chen, Kush Bhatia +3
Recent work has shown that language models' (LMs) prompt-based learning capabilities make them well suited for automating data labeling in domains where manual annotation is expens…
TART: A plug-and-play Transformer module for task-agnostic reasoning
Kush Bhatia, Avanika Narayan, Christopher De Sa +1
Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. In contrast, traditional…
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models
Alexander Pan, Kush Bhatia, Jacob Steinhardt
Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied. To understand how reward hacking ar…
Preference learning along multiple criteria: A game-theoretic perspective
Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett +2
The literature on ranking from ordinal data is vast, and there are several ways to aggregate overall preferences from pairwise comparisons between objects. In particular, it is wel…
Agnostic learning with unknown utilities
Kush Bhatia, Peter L. Bartlett, Anca D. Dragan +1
Traditional learning approaches for classification implicitly assume that each mistake has the same cost. In many real-world problems though, the utility of a decision depends on t…
Online learning with dynamics: A minimax perspective
Kush Bhatia, Karthik Sridharan
We study the problem of online learning with dynamics, where a learner interacts with a stateful environment over multiple rounds. In each round of the interaction, the learner sel…