5 papers · 1 filter
Towards a theory of inference-time alignment with unknown rewards
Steve Hanneke, Hongao Wang, Mingyue Xu
Generative model alignment has received broad interest, and significant progress has been made in supervised fine-tuning and inference-time computation. Yet, alignment has remained…
Optimal Learning Under Tsybakov Noise
Steve Hanneke, Hongao Wang, Mingyue Xu
Probably Approximately Correct (PAC) learning [Val84] is a fundamental learning model that has been extensively investigated. In this model, $\mathcal{H} \subseteq \{0,1\}^{\mathca…
Attention-based representations for multi-task computation
Daniel Hsu, Mingyue Xu
Multi-head attention layers produce vector representations that support multiple downstream tasks. We establish bounds on the number of heads required in two simple and concrete mu…
When More Data Doesn't Help: Limits of Adaptation in Multitask Learning
Steve Hanneke, Mingyue Xu
Multitask learning and related frameworks have achieved tremendous success in modern applications. In multitask learning problem, we are given a set of heterogeneous datasets colle…
To Grok Grokking: Provable Grokking in Ridge Regression
Mingyue Xu, Gal Vardi, Itay Safran
We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results for learning over-parameterized…