7 papers
Sequential-Innovation Reducibility and the Innovation Spectrum
Amir Leshem
Sequential prediction naturally induces an innovation sequence consisting of the prediction errors produced by a causal predictor. We use the collection of all such innovation sequ…
Universal Individual-Sequence Prediction with a Primitive-Recursive Superpredictor
Amir Leshem
We study sequential prediction of individual binary sequences under zero-one loss. No computable master can compete on every sequence with all total computable predictors. We there…
Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
Giseung Park, Hyunyoung Nam, Woohyeon Byeon +2
Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While max-min MORL has emerged as…
Computability Limits of Sequential Hypothesis Testing
Amir Leshem
Sequential hypothesis testing asks for decision rules that update as data arrive. A natural goal is \emph{eventual correctness}: the rule may change its mind early on, but it shoul…
Metastability-Containing Turing Machines
Johannes Bund, Amir Leshem, Moti Medina
Metastability is a spurious mode of operation in digital signals, where an electrical signal fails to settle into a stable state within a specified time, leading to uncertainty and…
Creating a digital poet
Vered Tohar, Tsahi Hayat, Amir Leshem
Can a machine write good poetry? Any positive answer raises fundamental questions about the nature and value of art. We report a seven-month poetry workshop in which a large langua…