Article List

With the goal of deploying generative AI systems, rater studies are becoming increasingly common and important. This means more and more researchers a...

Learn about the essential best practices for image labeling that can help you improve your computer vision model accuracy....

I wrote a (list of) regular expressions that will play a (not very good) chess game by running a 2-ply minimax search....

Most coders want AI to write code faster: I want AI to write FASTER CODE....

Recent advances in self-supervised learning have highlighted the efficacy of data augmentation in learning data representation from unlabeled data. Tr...

Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous st...

The paper focuses on mean-field type multi-agent control problems with finite state and action spaces where the dynamics and cost structures are symme...

Random reshuffling techniques are prevalent in large-scale applications, such as training neural networks. While the convergence and acceleration effe...

In contemporary data analysis, it is increasingly common to work with non-stationary complex data sets. These data sets typically extend beyond the cl...

First proposed by Seide (2014) as a heuristic, error feedback (EF) is a very popular mechanism for enforcing convergence of distributed gradient-based...

We explore multiple instance verification, a problem setting in which a query instance is verified against a bag of target instances with heterogeneou...

Representation multi-task learning (MTL) has achieved tremendous success in practice. However, the theoretical understanding of these methods is still...

Graphical models have been used extensively for modeling brain connectivity networks. However, unmeasured confounders and correlations among measureme...

We introduce distributional dynamic programming (DP) methods for optimizing statistical functionals of the return distribution, with standard reinforc...

We introduce a novel multi-armed bandit framework, where each arm is associated with a fixed unknown credal set over the space of outcomes (which can...

Training neural networks with first order optimisation methods is at the core of the empirical success of deep learning. The scale of initialisation i...

Hierarchical Reinforcement Learning (HRL) is a promising approach for managing task complexity across multiple levels of abstraction and accelerating...

We study quantitatively the overparametrization limit of the original Wasserstein-GAN algorithm. Effectively, we show that the algorithm is a stochast...