Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models …
Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is …
Multi-agent reinforcement learning has demonstrated significant potential in addressing complex cooperative tasks across various real-world applications. However, existing MARL …
In reinforcement learning and deep learning, softmax parameterization is commonly used to represent discrete probability distributions.In this work, we study three possible softmax …
We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is guaranteed to be convex and numerically tight. …
Although gradient descent with Polyak's momentum is widely used in modern machine and deep learning, a concrete understanding of its effects on the training trajectory remains …
Proposes a new active learning approach by proposing a new uncertainty measure called the least disagree metric, as well as its efficient estimator, which is proven to be …
Logistic bandit is a ubiquitous framework of modeling users' choices, e.g., click vs. no click for advertisement recommender system. We observe that the prior works overlook or …
We show that a simple trick of randomly corrupting the trajectories in Block MDPs allow for us to use the the clustering algorithm proposed of Jedra et al. (2023) for general …
Linear softmax parametrization (LSP) of a discrete probability distribution is ubiquitous in many areas, such as deep learning, RL, NLP, and social choice models. Instead of trying …