On Greedy Maximization of Entropy

Authors: Dravyansh Sharma, Ashish Kapoor, Amit Deshpande

ICML 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We provide empirical evidence that validates and highlights the key ideas in our result and their consequences. In this section, we empirically verify the applicability of our analysis on three real world data sets as tabulated in Table 1.
Researcher Affiliation Collaboration Dravyansh Sharma CS1110214@CSE.IITD.AC.IN IIT Delhi, New Delhi, India Amit Deshpande AMITDESH@MICROSOFT.COM Microsoft Research, Bangalore, India Ashish Kapoor AKAPOOR@MICROSOFT.COM Microsoft Research, Redmond, USA
Pseudocode Yes Algorithm 1 Greedy(f, k) Initialize S for t = 1 to k do imax argmax i/ S f(S {i}) f(S) S S {imax} end for Output S
Open Source Code No The paper does not provide concrete access to source code, nor does it state that source code is available in supplementary materials or via a specific link.
Open Datasets No The paper mentions data sets like 'IRIS', 'SONAR MINES', 'CLOUD' and refers to 'Intel Berkeley temperature data' with a citation to Krause et al. (2008), but does not provide specific links, DOIs, or full citations (including author/year within parentheses/brackets) for public access to the datasets used in their own experiments in Section 6.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning, nor does it explicitly mention a validation set.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers.
Experiment Setup No The paper mentions parameters like 'bandwidth parameter, γ' and 'scaling', but does not provide specific hyperparameter values, training configurations, or system-level settings in a way that would allow for clear reproduction of the experimental setup.