ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
The article discusses ACE (Off-Policy Actor-Critic with Causality-Aware Entropy Regularization), a novel reinforcement learning (RL) algorithm. Traditional…
A Framework for Variational Inference of Lightweight Bayesian Neural Networks with Heteroscedastic Uncertainties
The article discusses the importance of heteroscedastic predictive uncertainties in Bayesian Neural Networks (BNNs). The authors illustrate…
OmniPred: Language Models as Universal Regressors
The paper proposes OmniPred, a framework for training language models as universal regressors over evaluation data from…
Bandits with Abstention under Expert Advice
The article discusses the problem of prediction with expert advice under bandit feedback. The authors propose a…
Federated Complex Qeury Answering
The paper introduces FedCQA, a method to answer complex queries on multi-source knowledge graphs (KGs) while preserving…
latrend: A Framework for Clustering Longitudinal Data
The article introduces ‘latrend’, an R package developed for clustering longitudinal data, which is data gathered from…
Sparse Linear Regression and Lattice Problems
This paper presents a study on Sparse Linear Regression (SLR), a statistical problem of predicting a response…
CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations
The paper introduces a method based on Continuous Low Rank Adaptation (CoLoRA) that trains neural networks to…
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
The paper discusses adversarial training’s robustness-accuracy trade-off problem and proposes a solution. The authors focus on invariance…
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces
This article presents a Bayesian approach to off-policy evaluation (OPE) and off-policy learning (OPL) for large action…