Learning algorithms that divide the data into batches are prevalent in m...
In supervised batch learning, the predictive normalized maximum likeliho...
Detecting out-of-distribution (OOD) samples is vital for developing mach...
Adversarial attacks have been shown to be highly effective at degrading ...
A fundamental tenet of learning theory is that a trade-off exists betwee...
We consider the question of sequential prediction under the log-loss in ...
The predictive normalized maximum likelihood (pNML) approach has recentl...
The notion of implicit bias, or implicit regularization, has been sugges...
This paper present a one shot analysis of the lossy compression problem ...
Linear regression is a classical paradigm in statistics. A new look at i...
The Predictive Normalized Maximum Likelihood (pNML) scheme has been rece...
Universal supervised learning is considered from an information theoreti...
Typically, real-world stochastic processes are not easy to analyze. In t...
Canonical Correlation Analysis (CCA) is a linear representation learning...
Independent Component Analysis (ICA) is a statistical tool that decompos...
Estimating a large alphabet probability distribution from a limited numb...