SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.09057 · 2021

Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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; 1 honoured the contract we drafted, 3 violated it and 1 has no contract verdict; 8 failures of our instrument; 4 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/2110.09057.json · badge: /api/ran/2110.09057.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
kentaroy47/vision-transformers-cifar10 canonical (classifier label)
classifier basis not recorded on the link
13 ran · 4 no recorded run
FunctionStatusWhere it lives
ConvMixer Ran
ran; our contract draft was wrong, not the code
kentaroy47/vision-transformers-cifar10/models/convmixer.py
code served (permissive licence) · get_code("a7690d61376264fc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Sequential. The image it ran in was 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

torch.manual_seed(0)

# ConvMixer parameters:
# - dim: number of channels
# - depth: number of residual blocks
# - kernel_size: kernel size for depthwise convolutions
# - patch_size: patch size for initial embedding
# - n_classes: number of output classes

ARGS = {
    'dim': 8,
    'depth': 2,
    'kernel_size': 5,
    'patch_size': 4,
    'n_classes': 10
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential 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: none by the harness; any seed is in the setup block
FeedForward Ran
ran; our contract draft was wrong, not the code
kentaroy47/vision-transformers-cifar10/models/mlpmixer.py
pointer only (licence: MIT); the stored copy get_code serves, from xuwkk/task_aware_machine_unlearning, is pointer only (licence: NONE) · get_code("7ad86819c80a33c6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from xuwkk/task_aware_machine_unlearning, and GitHub detected no licence in that repository 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.

ResNet18 Ran
ran; our contract draft was wrong, not the code
kentaroy47/vision-transformers-cifar10/models/resnet.py
code served (permissive licence) · get_code("0f23e7e681845fe0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned ResNet. The image it ran in was 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

torch.manual_seed(0)

ARGS = {
    "num_classes": 10
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
ResNet50 Ran
ran; our contract draft was wrong, not the code
kentaroy47/vision-transformers-cifar10/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from jackbrocp/entaugment, is pointer only (licence: NONE) · get_code("21ba14c82993c2fe")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from jackbrocp/entaugment, and GitHub detected no licence in that repository 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.

conv_1x1_bn Ran
ran; our contract draft was wrong, not the code
kentaroy47/vision-transformers-cifar10/models/mobilevit.py
code served (permissive licence) · get_code("3fb34464dacbb0d3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. The image it ran in was 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

torch.manual_seed(0)

ARGS = {
    "inp": 3,
    "oup": 16,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
conv_nxn_bn Ran
ran; our contract draft was wrong, not the code
kentaroy47/vision-transformers-cifar10/models/mobilevit.py
code served (permissive licence) · get_code("e01bc963fa545868")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. The image it ran in was 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

torch.manual_seed(0)

ARGS = {
    'inp': 3,
    'oup': 16,
    'kernal_size': 3,
    'stride': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
convert_ln_to_dyt Ran
ran on a synthesized input
kentaroy47/vision-transformers-cifar10/models/dyt.py
code served (permissive licence) · get_code("4e79865ad6540be5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned SimpleModel. The image it ran in was 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
from torch import nn
from timm.models.layers import LayerNorm2d

torch.manual_seed(0)

# Create a simple module with LayerNorm that will be converted
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.ln1 = nn.LayerNorm(4)
        self.linear = nn.Linear(4, 3)
        self.ln2 = nn.LayerNorm(3)
        self.child_module = nn.Sequential(
            nn.LayerNorm(5),
            nn.Linear(5, 2)
        )
    
    def forward(self, x):
        x = self.ln1(x)
        x = self.linear(x)
        x = self.ln2(x)
        return x

# Instantiate the module to convert
module = SimpleModel()

ARGS = {
    'module': module
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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: none by the harness; any seed is in the setup block
create_mask Ran
ran, violated the contract we drafted
kentaroy47/vision-transformers-cifar10/models/swin.py
code served (permissive licence) · get_code("c0a5cd5e8d1e1870")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (16, 16) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
from einops import rearrange, repeat

torch.manual_seed(0)

ARGS = {
    "window_size": 4,
    "displacement": 1,
    "upper_lower": True,
    "left_right": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (16, 16) — shape (16, 16) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
dropout_layers Ran
ran; our contract draft was wrong, not the code
kentaroy47/vision-transformers-cifar10/models/cait.py
pointer only (licence: MIT); the stored copy get_code serves, from ztx-100/efficient_vit_with_dw, is pointer only (licence: NONE) · get_code("5c177b03eb4157b4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ztx-100/efficient_vit_with_dw, and GitHub detected no licence in that repository 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.

exists Ran
ran, violated the contract we drafted
kentaroy47/vision-transformers-cifar10/models/cait.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository 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.

get_relative_distances Ran
ran, honoured the contract we drafted
kentaroy47/vision-transformers-cifar10/models/swin.py
code served (permissive licence) · get_code("ea931f8eaca3c48c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family int, shape (9, 9, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

torch.manual_seed(0)

ARGS = {
    "window_size": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family int, shape (9, 9, 2) — shape (9, 9, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
pair Ran
ran, violated the contract we drafted
kentaroy47/vision-transformers-cifar10/models/dyt.py
code served (permissive licence) · get_code("6ba8cee9f5daea41")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

torch.manual_seed(0)

# The function 'pair' takes a single parameter 't' and returns it as a tuple if it isn't already one
# We need to test both cases: when t is a tuple and when it's not

# Case 1: t is not a tuple (e.g., an integer, string, tensor, etc.)
t_not_tuple = 5

# Case 2: t is already a tuple
t_is_tuple = (3, 7)

# We'll use the non-tuple case as the primary test
ARGS = {
    "t": t_not_tuple
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
posemb_sincos_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kentaroy47/vision-transformers-cifar10/models/simplevit.py
code served (permissive licence) · get_code("17f6d223949a7e58")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (12, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create a small patches tensor
# Shape: (batch, height, width, dim)
# The function unpacks this as: _, h, w, dim, device, dtype = (*patches.shape, patches.device, patches.dtype)
patches = torch.randn(2, 3, 4, 8, dtype=torch.float32)

ARGS = {
    "patches": patches,
    "temperature": 10000,
    "dtype": torch.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (12, 8) — shape (12, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: none by the harness; any seed is in the setup block
ResNet34 Not yet run
unverified (harvested, no recorded run)
kentaroy47/vision-transformers-cifar10/models/resnet.py
code served (permissive licence) · get_code("ac3dd06d1a08c549")
How it ran

no invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
kentaroy47/vision-transformers-cifar10/export_models.py
code served (permissive licence) · get_code("157f64840d3dfd7c")
How it ran

no invocation recorded.

mobilevit_xxs Not yet run
unverified (harvested, no recorded run)
kentaroy47/vision-transformers-cifar10/models/mobilevit.py
code served (permissive licence) · get_code("2e42a5b92c3a9f95")
How it ran

no invocation recorded.

swin_t Not yet run
unverified (harvested, no recorded run)
kentaroy47/vision-transformers-cifar10/models/swin.py
pointer only (licence: MIT); the stored copy get_code serves, from manyilee/plada, is pointer only (licence: NONE) · get_code("516538f47edf5014")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from manyilee/plada, and GitHub detected no licence in that repository 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 14 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 12 later) and 3 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
exists 486 other papers
64 dated earlier, 4 the same month, 416 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
pair 90 other papers
7 dated earlier, 82 later, 1 undated · 8 only as an assembly brick
2004.13649 (2020-04)
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2103.15691 (2021-03)
ViViT: A Video Vision Transformer
and 87 more not named here
ResNet18 27 other papers
7 dated earlier, 20 later
1605.07146 (2016-05)
Wide Residual Networks
1901.09847 (2019-01)
Error Feedback Fixes SignSGD and other Gradient Compression Schemes
1910.09652 (2019-10)
Kernelized Wasserstein Natural Gradient
and 24 more not named here
ResNet34 24 other papers
8 dated earlier, 16 later
1605.07146 (2016-05)
Wide Residual Networks
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2002.12047 (2020-02)
FMix: Enhancing Mixed Sample Data Augmentation
and 21 more not named here
ResNet50 14 other papers
4 dated earlier, 10 later
1605.07146 (2016-05)
Wide Residual Networks
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
2006.13554 (2020-06)
Normalized Loss Functions for Deep Learning with Noisy Labels
and 11 more not named here
get_relative_distances 6 other papers
1 dated earlier, 5 later · 2 only as an assembly brick
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2207.06405 (2022-07)
Masked Autoencoders that Listen
2303.07601 (2023-03)
V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception
and 3 more not named here
ConvMixer 5 other papers
5 later
136850512 (2022 (year only))
Rethinking Confidence Calibration for Failure Prediction
2201.09792 (2022-01)
Patches Are All You Need?
and 2 more not named here
posemb_sincos_2d 5 other papers
5 later
2204.00595 (2022-04)
Monarch: Expressive Structured Matrices for Efficient and Accurate Training
2205.03990 (2022-05)
Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
2304.06446 (2023-04)
SpectFormer: Frequency and Attention is what you need in a Vision Transformer
and 2 more not named here
FeedForward 4 other papers
1 dated earlier, 3 later
2105.01601 (2021-05)
MLP-Mixer: An all-MLP Architecture for Vision
2312.06330 (2023-12)
Navigating Open Set Scenarios for Skeleton-based Action Recognition
2401.02937 (2024-01)
Locally Adaptive Neural 3D Morphable Models
and 1 more not named here
create_mask 4 other papers
1 dated earlier, 3 later
2103.14030 (2021-03)
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
2207.06405 (2022-07)
Masked Autoencoders that Listen
2311.17243 (2023-11)
PHG-Net: Persistent Homology Guided Medical Image Classification
and 1 more not named here
dropout_layers 2 other papers
2 later
2308.03258 (2023-08)
APBench: A Unified Benchmark for Availability Poisoning Attacks and Defenses
2407.19394 (2024-07)
Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets
swin_t 2 other papers
2 later
2311.17243 (2023-11)
PHG-Net: Persistent Homology Guided Medical Image Classification
2506.20548 (2025-06)
Pay Less Attention to Deceptive Artifacts: Robust Detection of Compressed Deepfakes on Online Social Networks
conv_1x1_bn 1 other paper
1 the same month
2110.02178 (2021-10)
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
conv_nxn_bn 1 other paper
1 the same month
2110.02178 (2021-10)
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer

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

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on excessive tuning. Moreover, the calibrated fixed hyperparameter may not lead to optimal performance. In this paper, to eliminate the effort for tuning the momentum-related hyperparameter, we propose a new adaptive momentum inspired by the optimal choice of the heavy ball momentum for quadratic optimization. Our proposed adaptive heavy ball momentum can improve stochastic gradient descent (SGD) and Adam. SGD and Adam with the newly designed adaptive momentum are more robust to large learning rates, converge faster, and generalize better than the baselines. We verify the efficiency of SGD and Adam with the new adaptive momentum on extensive machine learning benchmarks, including image classification, language modeling, and machine translation. Finally, we provide convergence guarantees for SGD and Adam with the proposed adaptive momentum.

For agents

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

get_harvested_code_for_paper("2110.09057")
get_code_for_paper("2110.09057")
have("2110.09057")

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

curl https://syntology.ai/api/ran/2110.09057.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.09057.svg)](https://syntology.ai/paper/2110.09057)

Connect an agent — have() is free.