8 citations · 10 across the 11 of their papers we have counts for
15 papers · 1 filter
When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient
Shuning Shang, Hubert Strauss, Stanley Wei +2
Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely avail…
Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
Howard Chen, Noam Razin, Karthik Narasimhan +1
Adapting language models (LMs) to new tasks via post-training carries the risk of degrading existing capabilities -- a phenomenon classically known as catastrophic forgetting. In t…
What Makes a Reward Model a Good Teacher? An Optimization Perspective
Noam Razin, Zixuan Wang, Hubert Strauss +3
The success of Reinforcement Learning from Human Feedback (RLHF) critically depends on the quality of the reward model. However, while this quality is primarily evaluated through a…
The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels
Yonatan Slutzky, Yotam Alexander, Noam Razin +1
Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data. A recent class of neural network mode…
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization
Noam Razin, Sadhika Malladi, Adithya Bhaskar +3
Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences. Although these methods are designed to teach a mode…
Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning
Nadav Cohen, Noam Razin
These notes are based on a lecture delivered by NC on March 2021, as part of an advanced course in Princeton University on the mathematical understanding of deep learning. They pre…