Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sridhar, Anupama, Johansen, Alexander
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Convergence of TD(0) under Polynomial Mixing with Nonlinear Function Approximation
di: Sridhar, Anupama, et al.
Pubblicazione: (2025)

On the Local Complexity of Linear Regions in Deep ReLU Networks
di: Patel, Niket, et al.
Pubblicazione: (2024)

Discrete Functional Geometry of ReLU Networks via ReLU Transition Graphs
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators
di: Sridhar, Anupama, et al.
Pubblicazione: (2026)

SurvReLU: Inherently Interpretable Survival Analysis via Deep ReLU Networks
di: Sun, Xiaotong, et al.
Pubblicazione: (2024)

On Size-Independent Sample Complexity of ReLU Networks
di: Sellke, Mark
Pubblicazione: (2023)

Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks
di: Liao, Fangshuo, et al.
Pubblicazione: (2023)

The Geometry of ReLU Networks through the ReLU Transition Graph
di: Dhayalkar, Sahil Rajesh
Pubblicazione: (2025)

Complexity of Linear Regions in Self-supervised Deep ReLU Networks
di: Muthivhi, Mufhumudzi, et al.
Pubblicazione: (2026)

Complexity of One-Dimensional ReLU DNNs
di: Kogan, Jonathan, et al.
Pubblicazione: (2025)

On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth
di: Averkov, Gennadiy, et al.
Pubblicazione: (2025)

Convergence of Shallow ReLU Networks on Weakly Interacting Data
di: Dana, Léo, et al.
Pubblicazione: (2025)

Implicit Hypersurface Approximation Capacity in Deep ReLU Networks
di: Vallin, Jonatan, et al.
Pubblicazione: (2024)

N-ReLU: Zero-Mean Stochastic Extension of ReLU
di: Manik, Md Motaleb Hossen, et al.
Pubblicazione: (2025)

Complexity of Injectivity and Verification of ReLU Neural Networks
di: Froese, Vincent, et al.
Pubblicazione: (2024)

Computational Tradeoffs of Optimization-Based Bound Tightening in ReLU Networks
di: Badilla, Fabian, et al.
Pubblicazione: (2023)

The Resurrection of the ReLU
di: Horuz, Coşku Can, et al.
Pubblicazione: (2025)

Deep Network Approximation: Beyond ReLU to Diverse Activation Functions
di: Zhang, Shijun, et al.
Pubblicazione: (2023)

Towards Lower Bounds on the Depth of ReLU Neural Networks
di: Hertrich, Christoph, et al.
Pubblicazione: (2021)

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
di: Kim, Yujun, et al.
Pubblicazione: (2025)

Pathwise Explanation of ReLU Neural Networks
di: Lim, Seongwoo, et al.
Pubblicazione: (2025)

Convexity in ReLU Neural Networks: beyond ICNNs?
di: Gagneux, Anne, et al.
Pubblicazione: (2025)

Optimal Sets and Solution Paths of ReLU Networks
di: Mishkin, Aaron, et al.
Pubblicazione: (2023)

Online Realizable Regression and Applications for ReLU Networks
di: Doron-Arad, Ilan, et al.
Pubblicazione: (2026)

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks
di: Lee, Hyungu, et al.
Pubblicazione: (2025)

Why ReLU? A Bit-Model Dichotomy for Deep Network Training
di: Doron-Arad, Ilan, et al.
Pubblicazione: (2026)

Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
di: Yazdannik, Saman, et al.
Pubblicazione: (2025)

Sobolev Approximation of Deep ReLU Networks in Log-Barron Space
di: Song, Changhoon, et al.
Pubblicazione: (2026)

Directional Convergence, Benign Overfitting of Gradient Descent in leaky ReLU two-layer Neural Networks
di: Hashimoto, Ichiro
Pubblicazione: (2025)

Component-based Sketching for Deep ReLU Nets
di: Wang, Di, et al.
Pubblicazione: (2024)

On Space Folds of ReLU Neural Networks
di: Lewandowski, Michal, et al.
Pubblicazione: (2025)

Stochastic Bandits with ReLU Neural Networks
di: Xu, Kan, et al.
Pubblicazione: (2024)

ReLU-KAN: New Kolmogorov-Arnold Networks that Only Need Matrix Addition, Dot Multiplication, and ReLU
di: Qiu, Qi, et al.
Pubblicazione: (2024)

ReLU Networks for Model Predictive Control: Network Complexity and Performance Guarantees
di: Li, Xingchen, et al.
Pubblicazione: (2026)

Topological Expressivity of ReLU Neural Networks
di: Ergen, Ekin, et al.
Pubblicazione: (2023)

Three Quantization Regimes for ReLU Networks
di: Ou, Weigutian, et al.
Pubblicazione: (2024)

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

Approximation Error and Complexity Bounds for ReLU Networks on Low-Regular Function Spaces
di: Davis, Owen, et al.
Pubblicazione: (2024)

Deep ReLU Networks Have Surprisingly Simple Polytopes
di: Fan, Feng-Lei, et al.
Pubblicazione: (2023)

Causal Explanations from the Geometric Properties of ReLU Neural Networks
di: Woods, Hector, et al.
Pubblicazione: (2026)

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	"it"
VUFIND_SESSION	"bac4f3a1d051df90ba1d113eb6f8e37c"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790829849.3237 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "bac4f3a1d051df90ba1d113eb6f8e37c" ]`]
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=it; VUFIND_SESSION=bac4f3a1d051df90ba1d113eb6f8e37c; ui=standard"
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	"44756"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2505_15013/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2505_15013/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790829849.3193
REQUEST_TIME	1790829849

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler