Zobrazeno 1 - 10
of 3 952
pro vyhledávání: '"Verdun, A"'
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Autor:
Karvonen, Adam, Wright, Benjamin, Rager, Can, Angell, Rico, Brinkmann, Jannik, Smith, Logan, Verdun, Claudio Mayrink, Bau, David, Marks, Samuel
What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the quality of
Externí odkaz:
http://arxiv.org/abs/2408.00113
One of the most promising solutions for uncertainty quantification in high-dimensional statistics is the debiased LASSO that relies on unconstrained $\ell_1$-minimization. The initial works focused on real Gaussian designs as a toy model for this pro
Externí odkaz:
http://arxiv.org/abs/2407.18964
Over the last few years, debiased estimators have been proposed in order to establish rigorous confidence intervals for high-dimensional problems in machine learning and data science. The core argument is that the error of these estimators with respe
Externí odkaz:
http://arxiv.org/abs/2407.13575
Uncertainty quantification (UQ) is a crucial but challenging task in many high-dimensional regression or learning problems to increase the confidence of a given predictor. We develop a new data-driven approach for UQ in regression that applies both t
Externí odkaz:
http://arxiv.org/abs/2407.13666
Autor:
Oesterling, Alex, Verdun, Claudio Mayrink, Long, Carol Xuan, Glynn, Alexander, Paes, Lucas Monteiro, Vithana, Sajani, Cardone, Martina, Calmon, Flavio P.
Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups
Externí odkaz:
http://arxiv.org/abs/2407.08571
Model-based deep learning solutions to inverse problems have attracted increasing attention in recent years as they bridge state-of-the-art numerical performance with interpretability. In addition, the incorporated prior domain knowledge can make the
Externí odkaz:
http://arxiv.org/abs/2309.07982
Autor:
Schulz, Daniel F., Verdun, Amy
As the guardian of the euro, the European Central Bank (ECB) oversees a prime example of differentiated integration. Against the backdrop of the multiple crises of the euro’s second decade, this contribution asks how the ECB has dealt with differen
Externí odkaz:
https://library.oapen.org/handle/20.500.12657/54471
One of the most prominent methods for uncertainty quantification in high-dimen-sional statistics is the desparsified LASSO that relies on unconstrained $\ell_1$-minimization. The majority of initial works focused on real (sub-)Gaussian designs. Howev
Externí odkaz:
http://arxiv.org/abs/2212.14864
In many applications, solutions of numerical problems are required to be non-negative, e.g., when retrieving pixel intensity values or physical densities of a substance. In this context, non-negative least squares (NNLS) is a ubiquitous tool, e.g., w
Externí odkaz:
http://arxiv.org/abs/2207.08437
Autor:
Badiola, Laura Basterretxea, Milagro, Nuria Lainez, Lavín, Diego Cacho, Peraita, Sandra López, Ibarbia, Mikel Arruti, Kareaga, Mireia Martínez, Fernández del Rivero, Teresa de Portugal, Otero, Diego Soto de Prado, López, Valentín Alija, Fernández, Carlos Álvarez, Emborujo, Alejandra Lacalle, Arnaiz, Irene Gil, Rodríguez, Ricardo Fernández, Verdún-Aguilar, Juan, Sagastibeltza, Naiara, Duran, Ignacio
Publikováno v:
In Seminars in Oncology June-August 2024 51(3-4):77-86
