7 papers
Optimizing Transformer Neural Network for Real-Time Outlier Detection on FPGAs
Ilia Sobakinskikh, Paul Alexander Bilokon
In this work, we explore how the inference time of a Transformer Neural Network can be efficiently optimized with applications to real-time anomaly detection in financial time seri…
A Sieve on Rational Imbalances and the First Appearance of Denominators
Paul Alexander Bilokon
We construct a sieve that enumerates rational ``imbalances'' of the form for integers and , ordered lexicographically by . Each imbalance is…
Computation as a Game
Paul Alexander Bilokon
We present a unifying representation of computation as a two-player game between an \emph{Algorithm} and \emph{Nature}, grounded in domain theory and game theory. The Algorithm pro…
Simultaneous Novelty from First-Appearance Times in the Calkin-Wilf Enumeration
Paul Alexander Bilokon
We study the first-appearance map that assigns to each denominator the earliest breadth-first index at which a reduced fraction of denomina…
On the Density of Prime Imbalances in the Unit Interval
Paul Alexander Bilokon
We prove that the set of normalized differences between primes, defined as , is dense in the open unit interval . Our proof p…
Combining Deep Learning on Order Books with Reinforcement Learning for Profitable Trading
Koti S. Jaddu, Paul A. Bilokon
High-frequency trading is prevalent, where automated decisions must be made quickly to take advantage of price imbalances and patterns in price action that forecast near-future mov…
Implementing portfolio risk management and hedging in practice
Paul Alexander Bilokon
In academic literature portfolio risk management and hedging are often versed in the language of stochastic control and Hamilton--Jacobi--Bellman~(HJB) equations in continuous time…