7 citations · 10 across the 7 of their papers we have counts for
6 papers · 1 filter
In-Context Learning with Hypothesis-Class Guidance
Ziqian Lin, Shubham Kumar Bharti, Kangwook Lee
Recent research has investigated the underlying mechanisms of in-context learning (ICL) both theoretically and empirically, often using data generated from simple function classes.…
Optimally Teaching a Linear Behavior Cloning Agent
Shubham Kumar Bharti, Stephen Wright, Adish Singla +1
We study optimal teaching of Linear Behavior Cloning (LBC) learners. In this setup, the teacher can select which states to demonstrate to an LBC learner. The learner maintains a ve…
Provable Defense against Backdoor Policies in Reinforcement Learning
Shubham Kumar Bharti, Xuezhou Zhang, Adish Singla +1
We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adver…
The Game of Hidden Rules: A New Kind of Benchmark Challenge for Machine Learning
Eric Pulick, Shubham Bharti, Yiding Chen +4
As machine learning (ML) is more tightly woven into society, it is imperative that we better characterize ML's strengths and limitations if we are to employ it responsibly. Existin…
The Sample Complexity of Teaching-by-Reinforcement on Q-Learning
Xuezhou Zhang, Shubham Kumar Bharti, Yuzhe Ma +2
We study the sample complexity of teaching, termed as "teaching dimension" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the studen…
On the relationship between multitask neural networks and multitask Gaussian Processes
Karthikeyan K, Shubham Kumar Bharti, Piyush Rai
Despite the effectiveness of multitask deep neural network (MTDNN), there is a limited theoretical understanding on how the information is shared across different tasks in MTDNN. I…