Search Results for author:
Found 5 papers, 1 papers with code
Settling Constant Regrets in Linear Markov Decision Processes
To the best of our knowledge, Cert-LSVI-UCB is the first algorithm to achieve a constant, instance-dependent, high-probability regret bound in RL with linear function approximation for infinite runs without relying on prior distribution assumptions.
Efficient Data Learning for Open Information Extraction with Pre-trained Language Models
Open Information Extraction (OpenIE) is a fundamental yet challenging task in Natural Language Processing, which involves extracting all triples (subject, predicate, object) from a given sentence.
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
We show that, when the misspecification level $\zeta$ is dominated by $\tilde O (\Delta / \sqrt{d})$ with $\Delta$ being the minimal sub-optimality gap and $d$ being the dimension of the contextual vectors, our algorithm enjoys the same gap-dependent regret bound $\tilde O (d^2/\Delta)$ as in the well-specified setting up to logarithmic factors.
OpenFE: Automated Feature Generation with Expert-level Performance
In the two competitions, features generated by OpenFE with a simple baseline model can beat 99. 3% and 99. 6% data science teams respectively.
Efficient Algorithms for Sparse Moment Problems without Separation
Our algorithm for the one-dimensional problem (also called the sparse Hausdorff moment problem) is a robust version of the classic Prony's method, and our contribution mainly lies in the analysis.
