Online combinatorial optimization with stochastic decision sets and adversarial losses

Authors: Gergely Neu, Michal Valko

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section we present the empirical evaluation of our algorithms for bandit and semi-bandit settings, and compare them to its counterparts [13].
Researcher Affiliation Academia Gergely Neu Michal Valko Seque L team, INRIA Lille Nord Europe, France {gergely.neu,michal.valko}@inria.fr
Pseudocode No Figure 1 presents a protocol for interaction, but it is not pseudocode or a clearly labeled algorithm block describing the implementation of SLEEPINGCAT or SLEEPINGCATBANDIT.
Open Source Code No The paper does not provide any statement about releasing source code or a link to a code repository.
Open Datasets No The paper describes how losses are constructed (e.g., 'Losses for each arm are constructed as random walks with Gaussian increments') and problems are set up (e.g., 'shortest path problem on grids') but does not reference or provide access information for any publicly available or open datasets.
Dataset Splits No The paper does not specify exact training, validation, or test dataset splits, percentages, or sample counts.
Hardware Specification No The paper does not provide specific details about the hardware used for experiments, such as GPU or CPU models.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9).
Experiment Setup Yes We consider an experiment with T = 10,000 and 5 arms, each of which are available independenly of each other with probability p. Losses for each arm are constructed as random walks with Gaussian increments of standard deviation 0.002, initialized uniformly on [0, 1]. To evaluate SLEEPINGCATBANDIT in the semi-bandit setting, we consider the shortest path problem on grids of 3x3 and 10x10 nodes... The individual availability of each edge is sampled with probability 0.9, independently of the others.