Learning Gaussian DAG Models without Condition Number Bounds

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Daskalakis, Constantinos, Kandiros, Vardis, Yao, Rui
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Estimating Ising Models in Total Variation Distance
par: Daskalakis, Constantinos, et autres
Publié: (2025)

The Conflict Graph Design: Estimating Causal Effects under Arbitrary Neighborhood Interference
par: Kandiros, Vardis, et autres
Publié: (2024)

Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'?
par: Daskalakis, Constantinos, et autres
Publié: (2024)

Learning High-dimensional Gaussians from Censored Data
par: Bhattacharyya, Arnab, et autres
Publié: (2025)

The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
par: Daskalakis, Constantinos, et autres
Publié: (2018)

Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization
par: Daskalakis, Constantinos, et autres
Publié: (2018)

How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion
par: Daras, Giannis, et autres
Publié: (2024)

Fixed Point Computation: Beating Brute Force with Smoothed Analysis
par: Attias, Idan, et autres
Publié: (2025)

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data
par: Daras, Giannis, et autres
Publié: (2024)

On Sampling from Ising Models with Spectral Constraints
par: Galanis, Andreas, et autres
Publié: (2024)

Maximizing utility in multi-agent environments by anticipating the behavior of other learners
par: Assos, Angelos, et autres
Publié: (2024)

Near-Optimal Learning and Planning in Separated Latent MDPs
par: Chen, Fan, et autres
Publié: (2024)

High-accuracy sampling for diffusion models and log-concave distributions
par: Chen, Fan, et autres
Publié: (2026)

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
par: Hosseintabar, Danial, et autres
Publié: (2025)

Analytic DAG Constraints for Differentiable DAG Learning
par: Zhang, Zhen, et autres
Publié: (2025)

Ambient Diffusion Omni: Training Good Models with Bad Data
par: Daras, Giannis, et autres
Publié: (2025)

High-accuracy log-concave sampling with stochastic queries
par: Chen, Fan, et autres
Publié: (2026)

From External to Swap Regret 2.0: An Efficient Reduction and Oblivious Adversary for Large Action Spaces
par: Dagan, Yuval, et autres
Publié: (2023)

Proximal Regret and Proximal Correlated Equilibria: A New Tractable Solution Concept for Online Learning and Games
par: Cai, Yang, et autres
Publié: (2025)

Smooth Nash Equilibria: Algorithms and Complexity
par: Daskalakis, Constantinos, et autres
Publié: (2023)

A novel hybrid approach for positive-valued DAG learning
par: Zhao, Yao
Publié: (2026)

$ψ$DAG: Projected Stochastic Approximation Iteration for DAG Structure Learning
par: Ziu, Klea, et autres
Publié: (2024)

DAG Learning from Zero-Inflated Count Data Using Continuous Optimization
par: Sato, Noriaki, et autres
Publié: (2025)

Ambient Dataloops: Generative Models for Dataset Refinement
par: Rodríguez-Muñoz, Adrián, et autres
Publié: (2026)

On Tractable $Φ$-Equilibria in Non-Concave Games
par: Cai, Yang, et autres
Publié: (2024)

ExDAG: an MIQP Algorithm for Learning DAGs
par: Rytir, Pavel, et autres
Publié: (2024)

Exploiting Non-Negativity in DAG Structure Learning
par: Rey, Samuel, et autres
Publié: (2026)

Breaking the $T^{2/3}$ Barrier for Sequential Calibration
par: Dagan, Yuval, et autres
Publié: (2024)

Non-negative Weighted DAG Structure Learning
par: Rey, Samuel, et autres
Publié: (2024)

SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation
par: Zhou, Xinyi, et autres
Publié: (2024)

A Novel Theoretical Analysis for Clustering Heteroscedastic Gaussian Data without Knowledge of the Number of Clusters
par: Pastor, Dominique, et autres
Publié: (2026)

Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery
par: Darvariu, Victor-Alexandru, et autres
Publié: (2023)

Diverging Flows: Detecting Extrapolations in Conditional Generation
par: Tsakonas, Constantinos, et autres
Publié: (2026)

DAG-aware Transformer for Causal Effect Estimation
par: Liu, Manqing, et autres
Publié: (2024)

DAG DECORation: Continuous Optimization for Structure Learning under Hidden Confounding
par: Pal, Samhita, et autres
Publié: (2025)

Non-negative DAG Learning from Time-Series Data
par: Rey, Samuel, et autres
Publié: (2025)

CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Data
par: Soatto, Renzo G., et autres
Publié: (2026)

MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
par: Li, Dong, et autres
Publié: (2026)

Model Immunization from a Condition Number Perspective
par: Zheng, Amber Yijia, et autres
Publié: (2025)

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
VUFIND_SESSION	"8e9c674bfa6c224f50f0861b8975c5e8"
ui	"standard"
language	"fr"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790882240.6355 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "8e9c674bfa6c224f50f0861b8975c5e8" ]`]
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	"VUFIND_SESSION=8e9c674bfa6c224f50f0861b8975c5e8; ui=standard; language=fr"
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	"216.73.217.142"
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	"56690"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2511_06164/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2511_06164/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790882240.6156
REQUEST_TIME	1790882240

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler