A statistical perspective on distillation

Authors: Aditya K Menon, Ankit Singh Rawat, Sashank Reddi, Seungyeon Kim, Sanjiv Kumar

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our findings are verified for linear models, neural networks, and decision trees, on both controlled synthetic and real-world datasets.
Researcher Affiliation Industry 1Google Research, New York. Correspondence to: Aditya Krishna Menon <adityakmenon@google.com>.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes On CIFAR-100, we train teachers that are Res Nets of varying depths, and distill these to a student Res Net of fixed depth 8. ... multiclass retrieval, AMAZONCAT-13K and AMAZONCAT-670K (Mc Auley & Leskovec, 2013; Bhatia et al., 2015).
Dataset Splits No The paper mentions training and test sets but does not explicitly provide details about a validation set or its split.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with versions).
Experiment Setup Yes On CIFAR-100, we train teachers that are Res Nets of varying depths, and distill these to a student Res Net of fixed depth 8. ... We use a feedforward teacher model with a single (linear) hidden layer of width 512, trained to minimise the softmax cross-entropy. For the student , we make the hidden layer width 8 for AMAZONCAT-13K and 64 for AMAZONCAT-670K. ... apply temperature scaling with T 2 {1.0, 1.5, 2.0, . . . , 5.0}.