Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

No-regret Algorithms for Capturing Events in Poisson Point Processes

Authors: Mojmir Mutny, Andreas Krause

ICML 2021 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the practicality of the method on problems from crime modeling, revenue maximization as well as environmental monitoring. 7. Experiments and Applications In our experiments, we investigate both feedback models as well as different cost models: uniform cost w(A) = |A|, concave cost w(A) = |A| + 0.01, and one-off cost.
Researcher Affiliation Academia Mojmír Mutný 1 Andreas Krause 1 1Department of Computer Science, ETH Zurich, Zurich, Switzerland. Correspondence to: Mojmír Mutný <EMAIL>.
Pseudocode Yes Algorithm 1 CAPTURE-UCB Require: cost function wt, partition (schedule) B, t = 1 1: while t T do 2: Estimate ˆλ as in (3) 3: At = arg max A A ucbt(A) wt(A) as in (10) 4: Sense At for time 5: Receive: ( n(B At) for B B if count-record n(At) if histogram 6: t = t + 1. 7: end while
Open Source Code No The paper does not explicitly provide access to source code for the methodology described.
Open Datasets Yes We use a crime dataset released by the San Francisco police department to estimate the intensity of burglary occurrences over space (see Fig. in Appendix D). We use two datasets from Baddeley et al. (2015), one containing locations of an African tree shrub Beilschmiedia, and one containing Gorilla nesting locations in a Cameroon rain forest.
Dataset Splits No The paper does not provide specific dataset split information (e.g., exact percentages or sample counts for training, validation, and test sets) for the experiments conducted.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies, such as library names with version numbers, used to replicate the experiments.
Experiment Setup Yes In our experiments, we investigate both feedback models as well as different cost models: uniform cost w(A) = |A|, concave cost w(A) = |A| + 0.01, and one-off cost. Confidence parameter We relax the theoretical requirements of the confidence sets, and simply use β = 4, as well as tweak the past... The remaining experiments are with tweaking, β = 4 and γ = 1.