Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Worschech, Roman, Rosenow, Bernd
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
von: Kühn, Marcel, et al.
Veröffentlicht: (2026)

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
von: Defilippis, Leonardo, et al.
Veröffentlicht: (2025)

AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
von: Neumann, Oren, et al.
Veröffentlicht: (2024)

Breaking Neural Network Scaling Laws with Modularity
von: Boopathy, Akhilan, et al.
Veröffentlicht: (2024)

Enhancing Noise-Robust Losses for Large-Scale Noisy Data Learning
von: Staats, Max, et al.
Veröffentlicht: (2023)

Scaling Laws for Emulation of Stellar Spectra
von: Różański, Tomasz, et al.
Veröffentlicht: (2025)

Unified Neural Network Scaling Laws and Scale-time Equivalence
von: Boopathy, Akhilan, et al.
Veröffentlicht: (2024)

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks
von: Lee, Dongwoo, et al.
Veröffentlicht: (2025)

Neural Neural Scaling Laws
von: Hu, Michael Y., et al.
Veröffentlicht: (2026)

On the Invariance and Generality of Neural Scaling Laws
von: Han, Xing, et al.
Veröffentlicht: (2026)

Neural Scaling Laws Rooted in the Data Distribution
von: Brill, Ari
Veröffentlicht: (2024)

Topological gap protocol based machine learning optimization of Majorana hybrid wires
von: Thamm, Matthias, et al.
Veröffentlicht: (2023)

Scaling Laws for Optimal Data Mixtures
von: Shukor, Mustafa, et al.
Veröffentlicht: (2025)

Configuration-to-Performance Scaling Law with Neural Ansatz
von: Zhang, Huaqing, et al.
Veröffentlicht: (2026)

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling
von: Li, Chaojian, et al.
Veröffentlicht: (2025)

Towards Neural Scaling Laws on Graphs
von: Liu, Jingzhe, et al.
Veröffentlicht: (2024)

Explaining Neural Scaling Laws
von: Bahri, Yasaman, et al.
Veröffentlicht: (2021)

On the Optimizer Dependence of Neural Scaling Laws
von: Ramani, Vansh, et al.
Veröffentlicht: (2026)

Scaling Laws are Redundancy Laws
von: Bi, Yuda, et al.
Veröffentlicht: (2025)

Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models
von: Vaidhya, Tejas, et al.
Veröffentlicht: (2025)

Müntz-Szász Networks: Neural Architectures with Learnable Power-Law Bases
von: N'guessan, Gnankan Landry Regis
Veröffentlicht: (2025)

Neural Scaling Laws for Deep Regression
von: Cadez, Tilen, et al.
Veröffentlicht: (2025)

Scaling Laws for Neural Material Models
von: Trikha, Akshay, et al.
Veröffentlicht: (2025)

Zero-One Laws of Graph Neural Networks
von: Adam-Day, Sam, et al.
Veröffentlicht: (2023)

Information-Theoretic Foundations for Neural Scaling Laws
von: Jeon, Hong Jun, et al.
Veröffentlicht: (2024)

Scaling Laws of Machine Learning for Optimal Power Flow
von: Liu, Xinyi, et al.
Veröffentlicht: (2026)

Scaling Laws and Pathologies of Single-Layer PINNs: Network Width and PDE Nonlinearity
von: Chaudhry, Faris
Veröffentlicht: (2026)

Towards Scaling Law Analysis For Spatiotemporal Weather Data
von: Kiefer, Alexander, et al.
Veröffentlicht: (2026)

Renormalizable Spectral-Shell Dynamics as the Origin of Neural Scaling Laws
von: Zhang, Yizhou
Veröffentlicht: (2025)

Complexity Scaling Laws for Neural Models using Combinatorial Optimization
von: Weissman, Lowell, et al.
Veröffentlicht: (2025)

On Neural Scaling Laws for Weather Emulation through Continual Training
von: Subramanian, Shashank, et al.
Veröffentlicht: (2026)

How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines
von: Sengupta, Ayan, et al.
Veröffentlicht: (2025)

Neural Scaling Laws of Deep ReLU and Deep Operator Network: A Theoretical Study
von: Liu, Hao, et al.
Veröffentlicht: (2024)

gzip Predicts Data-dependent Scaling Laws
von: Pandey, Rohan
Veröffentlicht: (2024)

Prescriptive Scaling Laws for Data Constrained Training
von: Lovelace, Justin, et al.
Veröffentlicht: (2026)

Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
von: Goyal, Sachin, et al.
Veröffentlicht: (2024)

A Dynamical Model of Neural Scaling Laws
von: Bordelon, Blake, et al.
Veröffentlicht: (2024)

Scaling Laws for the Value of Individual Data Points in Machine Learning
von: Covert, Ian, et al.
Veröffentlicht: (2024)

Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
von: Jiang, Yiding, et al.
Veröffentlicht: (2024)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"de"
ui	"standard"
VUFIND_SESSION	"ca4f1eef77b262e3ff70f1c3da7fb971"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790741964.248 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "ca4f1eef77b262e3ff70f1c3da7fb971" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"language=de; ui=standard; VUFIND_SESSION=ca4f1eef77b262e3ff70f1c3da7fb971"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.216.147"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"4820"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2410_09005/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2410_09005/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790741964.2428
REQUEST_TIME	1790741964

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler