SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.00359 · NeurIPS · 2023

Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training

Tianyu Pang, Michael Mahoney, Yaoqing Yang, Yefan Zhou, Charles Martin, Keqin Liu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 1 has no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2312.00359.json · badge: /api/ran/2312.00359.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
yefanzhou/tempbalance marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Tempbalance Ran
ran on a synthesized input
yefanzhou/tempbalance/tempbalance.py
code served (permissive licence) · get_code("5dc7fcceddd81d49")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import math
import pandas as pd
import numpy as np
from operator import itemgetter

# Create a simple test network
class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 8, kernel_size=3, padding=1)
        self.bn1 = nn.BatchNorm2d(8)
        self.conv2 = nn.Conv2d(8, 16, kernel_size=3, padding=1)
        self.bn2 = nn.BatchNorm2d(16)
        self.linear1 = nn.Linear(16, 8)
        self.ln1 = nn.LayerNorm(8)
        self.linear2 = nn.Linear(8, 4)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x = x.view(x.size(0), -1)
        x = self.linear1(x)
        x = self.ln1(x)
        x = self.linear2(x)
        return x

net = SimpleNet()

INIT_ARGS = {
    'net': net,
    'EVALS_THRESH': 1e-05,
    'bins': 100,
    'conv_norm': 0.5,
    'pl_fitting': 'median',
    'xmin_pos': 2,
    'filter_zeros': False,
    'remove_first_layer': True,
    'remove_last_layer': True,
    'eigs_thresh': 50,
    'esd_metric_for_tb': 'alpha',
    'assign_func': 'tb_linear_map',
    'lr_min_ratio': 0.5,
    'lr_max_ratio': 1.5,
    'batchnorm': True,
    'batchnorm_type': 'name',
    'layernorm': False,
}

ARGS = {
    'untuned_lr': 0.1,
    'initialize': True,
}

METHOD = 'build_optimizer_param_group'
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, pandas, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

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

Regularization in modern machine learning is crucial, and it can take various forms in algorithmic design: training set, model family, error function, regularization terms, and optimizations. In particular, the learning rate, which can be interpreted as a temperature-like parameter within the statistical mechanics of learning, plays a crucial role in neural network training. Indeed, many widely adopted training strategies basically just define the decay of the learning rate over time. This process can be interpreted as decreasing a temperature, using either a global learning rate (for the entire model) or a learning rate that varies for each parameter. This paper proposes TempBalance, a straightforward yet effective layer-wise learning rate method. TempBalance is based on Heavy-Tailed Self-Regularization (HT-SR) Theory, an approach which characterizes the implicit self-regularization of different layers in trained models. We demonstrate the efficacy of using HT-SR-motivated metrics to guide the scheduling and balancing of temperature across all network layers during model training, resulting in improved performance during testing. We implement TempBalance on CIFAR10, CIFAR100, SVHN, and TinyImageNet datasets using ResNets, VGGs and WideResNets with various depths and widths. Our results show that TempBalance significantly outperforms ordinary SGD and carefully-tuned spectral norm regularization. We also show that TempBalance outperforms a number of state-of-the-art optimizers and learning rate schedulers.

For agents

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

get_harvested_code_for_paper("2312.00359")
get_code_for_paper("2312.00359")
have("2312.00359")

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

curl https://syntology.ai/api/ran/2312.00359.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.00359.svg)](https://syntology.ai/paper/2312.00359)

Connect an agent — have() is free.