Tootfinder

Unregularized limit of stochastic gradient method for Wasserstein distributionally robust optimization
Tam Le (LPSM, UPCit\'e)
https://arxiv.org/abs/2506.04948

Unregularized limit of stochastic gradient method for Wasserstein distributionally robust optimization
Distributionally robust optimization offers a compelling framework for model fitting in machine learning, as it systematically accounts for data uncertainty. Focusing on Wasserstein distributionally robust optimization, we investigate the regularized problem where entropic smoothing yields a sampling-based approximation of the original objective. We establish the convergence of the approximate gradient over a compact set, leading to the concentration of the regularized problem critical points o…

On the Benefits of Accelerated Optimization in Robust and Private Estimation
Laurentiu Andrei Marchis, Po-Ling Loh
https://arxiv.org/abs/2506.03044 https:/…

On the Benefits of Accelerated Optimization in Robust and Private Estimation
We study the advantages of accelerated gradient methods, specifically based on the Frank-Wolfe method and projected gradient descent, for privacy and heavy-tailed robustness. Our approaches are as follows: For the Frank-Wolfe method, our technique is based on a tailored learning rate and a uniform lower bound on the gradient of the $\ell_2$-norm over the constraint set. For accelerating projected gradient descent, we use the popular variant based on Nesterov's momentum, and we optimize our obje…

Hat gedauert, aber den sogenannten Podcast "Die Peter Thiel Story" gibt's seit heute auch wirklich als Podcast (Folge 1-3/6).
https://www.deutschlandfunk.de/die-peter-thiel-story-100.html

Die Peter Thiel Story
Peter Thiel ist der Strippenzieher hinter dem kulturellen Rechtsruck in den USA und einer der wichtigsten Unterstützer von Donald Trump. Mit Paypal und Facebook ist er reich geworden. Das ist die Geschichte des geheimnisvollen Tech-Milliardärs.

This https://arxiv.org/abs/2505.01874 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Towards Trustworthy Federated Learning with Untrusted Participants
Resilience against malicious participants and data privacy are essential for trustworthy federated learning, yet achieving both with good utility typically requires the strong assumption of a trusted central server. This paper shows that a significantly weaker assumption suffices: each pair of participants shares a randomness seed unknown to others. In a setting where malicious participants may collude with an untrusted server, we propose CafCor, an algorithm that integrates robust gradient agg…

Stabilization of the Gradient Method for Solving Linear Algebraic Systems - A Method Related to the Normal Equation
Ibrahima Dione
https://arxiv.org/abs/2506.00702

Stabilization of the Gradient Method for Solving Linear Algebraic Systems - A Method Related to the Normal Equation
Although it is relatively easy to apply, the gradient method often displays a disappointingly slow rate of convergence. Its convergence is specially based on the structure of the matrix of the algebraic linear system, and on the choice of the stepsize defining the new iteration. We propose here a simple and robust stabilization of the gradient method, which no longer assumes a structure on the matrix (neither symmetric, nor positive definite) to converge, and which no longer requires an approac…

When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR
Dayoon Ko, Jinyoung Kim, Sohyeon Kim, Jinhyuk Kim, Jaehoon Lee, Seonghak Song, Minyoung Lee, Gunhee Kim
https://arxiv.org/abs/2506.01877

When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR
Dense retrievers encode texts into embeddings to efficiently retrieve relevant documents from large databases in response to user queries. However, real-world corpora continually evolve, leading to a shift from the original training distribution of the retriever. Without timely updates or retraining, indexing newly emerging documents can degrade retrieval performance for future queries. Thus, identifying when a dense retriever requires an update is critical for maintaining robust retrieval syst…

Reposted with alt
https://mastodon.social/@VeroniqueB99/114604050608739836

Vee (@VeroniqueB99@mastodon.social)
Attached: 1 image

This https://arxiv.org/abs/2505.18378 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Metallicities of old open clusters: a new Galactic map
Old open clusters can constrain the chemical evolution of the Galactic disc through their metallicity gradients and age-metallicity relation but they suffer from low statistics. This work aims to determine precise and homogeneous metallicities for a number of old ($\geq$ 500 Myr) clusters from all-sky catalogues of stellar parameters leveraging Gaia spectrophotometry. Our purpose was to revisit the metallicity distribution of the oldest open clusters as a function of their Galactic position and…

This https://arxiv.org/abs/2506.02635 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Efficient Quadratic Corrections for Frank-Wolfe Algorithms
We develop a Frank-Wolfe algorithm with corrective steps, generalizing previous algorithms including blended pairwise conditional gradients and fully-corrective Frank-Wolfe, and propose a highly efficient corrective algorithm in the case of convex quadratic objectives based on linear optimization or linear system solving, akin to Wolfe's minimum-norm point. Beyond optimization problems that are directly quadratic, we revisit two algorithms, split conditional gradient for the intersection of two…

Efficient Quadratic Corrections for Frank-Wolfe Algorithms
Jannis Halbey, Seta Rakotomandimby, Mathieu Besan\c{c}on, Sebastian Pokutta
https://arxiv.org/abs/2506.02635

Efficient Quadratic Corrections for Frank-Wolfe Algorithms
We develop a Frank-Wolfe algorithm with corrective steps, generalizing previous algorithms including blended pairwise conditional gradients and fully-corrective Frank-Wolfe, and propose a highly efficient corrective algorithm in the case of convex quadratic objectives based on linear optimization or linear system solving, akin to Wolfe's minimum-norm point. Beyond optimization problems that are directly quadratic, we revisit two algorithms, split conditional gradient for the intersection of two…