Learning Optimal Commitment to Overcome Insecurity

Authors: Avrim Blum, Nika Haghtalab, Ariel D Procaccia

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We design an algorithm that learns an (additively) ϵ-optimal strategy for the defender with probability 1 δ, by asking a number of queries that is polynomial in the representation of the security game, and logarithmic in 1/ϵ and 1/δ.
Researcher Affiliation Academia Avrim Blum Carnegie Mellon University avrim@cs.cmu.edu Nika Haghtalab Carnegie Mellon University nika@cmu.edu Ariel D. Procaccia Carnegie Mellon University arielpro@cs.cmu.edu
Pseudocode Yes Algorithm 1 LATTICE-ROUNDING (approximately optimal strategy p) Algorithm 2 OPTIMIZE (accuracy ϵ, confidence δ)
Open Source Code No The paper does not provide any links to open-source code or explicitly state that code for the described methodology is available.
Open Datasets No The paper is theoretical and focuses on algorithm design and complexity analysis in a game-theoretic context. It does not use or refer to any publicly available or open datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with dataset splits (e.g., training, validation, test splits).
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for computations or experiments.
Software Dependencies No The paper is theoretical and focuses on algorithms and proofs. It does not mention any specific software dependencies or their version numbers (e.g., programming languages, libraries, solvers) that would be needed for implementation.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details, hyperparameters, or system-level training settings.