SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.01484 · 2026

SGD-Based Knowledge Distillation with Bayesian Teachers: Theory and Guidelines

Yonina Eldar, Itai Morad, Nir Shlezinger

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2601.01484.json · badge: /api/ran/2601.01484.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
iclr2024mcmi/ICLRMCMI canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_teacher_name Ran
ran; our contract draft was wrong, not the code
iclr2024mcmi/ICLRMCMI/CIFAR100-FewShot/FineTuneTeacher.py
pointer only (licence: NONE) · get_code("4b4f0463521302e8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iclr2024mcmi/ICLRMCMI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

covariance_loss Not yet run
unverified (harvested, no recorded run)
iclr2024mcmi/ICLRMCMI/CIFAR100-FewShot/losses.py
pointer only (licence: NONE) · get_code("753c62e00dde9126")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iclr2024mcmi/ICLRMCMI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_teacher_name 6 other papers
6 dated earlier
1910.10699 (2019-10)
Contrastive Representation Distillation
2011.01424 (2020-11)
Distilling Knowledge by Mimicking Features
2106.04570 (2021-06)
BERT Learns to Teach: Knowledge Distillation with Meta Learning
and 3 more not named here
covariance_loss 1 other paper
1 dated earlier
2103.14021 (2021-03)
Orthogonal Projection Loss

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs. While KD has shown strong empirical success in numerous applications, its theoretical underpinnings remain only partially understood. In this work, we adopt a Bayesian perspective on KD to rigorously analyze the convergence behavior of students trained with Stochastic Gradient Descent (SGD). We study two regimes: (i) when the teacher provides the exact Bayes Class Probabilities (BCPs); and (ii) supervision with noisy approximations of the BCPs. Our analysis shows that learning from BCPs yields variance reduction and removes neighborhood terms in the convergence bounds compared to one-hot supervision. We further characterize how the level of noise affects generalization and accuracy. Motivated by these insights, we advocate the use of Bayesian deep learning models, which typically provide improved estimates of the BCPs, as teachers in KD. Consistent with our analysis, we experimentally demonstrate that students distilled from Bayesian teachers not only achieve higher accuracies (up to +4.27%), but also exhibit more stable convergence (up to 30% less noise), compared to students distilled from deterministic teachers.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.01484")
get_code_for_paper("2601.01484")
have("2601.01484")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2601.01484.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2601.01484.svg)](https://syntology.ai/paper/2601.01484)

Connect an agent — have() is free.