paper-conference

Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation …

Multi-agent reinforcement learning has demonstrated significant potential in addressing complex cooperative tasks across various …

We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is …

Although gradient descent with Polyak’s momentum is widely used in modern machine and deep learning, a concrete understanding of …

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 asymptotically consistent. This is then combined with seeding to become a new active learning algorith, LDM-S, which is shown to outperform existing approaches across various architectures and datasets.

Logistic bandit is a ubiquitous framework of modeling users’ choices, e.g., click vs. no click for advertisement recommender …

Proposes a framework for performing fair PCA in memory limited, streaming setting. Sample complexity results and empirical discussions show the superiority of our approach compared to the existing approaches.

A novel problem setting where heterogeneous multi-agent bandits collaborate over a network to minimize their group regret. To deal with the high communication complexity of the classic flooding protocol combined with UCB, a new network protocol called Flooding with Absorption (FwA) is proposed. Theoretical and empirical analyses are provded for flooding and FwA, showing the efficacy of our proposed FwA.

First theoretical analysis of model estimation and reward-free RL of block MDP, without resorting to function approximation frameworks. Lower bounds and algorithms with near-optimal upper bound are provided.

Proposes a new MMD-based definition of fairness for PCA, then formulate fair PCA as an optimization over the Stiefel manifold. Various theoretical and empirical discussions show the superiority of our approach compared to the existing approach (Olfat & Aswani, AAAI'19).