Tootfinder

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/5]:
- Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization a...
Haoyue Bai, Gregory Canal, Xuefeng Du, Jeongyeol Kwon, Robert Nowak, Yixuan Li
https://arxiv.org/abs/2306.09158
- Sparse, Efficient and Explainable Data Attribution with DualXDA
Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
https://arxiv.org/abs/2402.12118 https://mastoxiv.page/@arXiv_csLG_bot/111962593972369958
- HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs
Sun, Que, {\AA}rrestad, Loncar, Ngadiuba, Luk, Spiropulu
https://arxiv.org/abs/2405.00645 https://mastoxiv.page/@arXiv_csLG_bot/112370274737558603
- On the Identification of Temporally Causal Representation with Instantaneous Dependence
Li, Shen, Zheng, Cai, Song, Gong, Chen, Zhang
https://arxiv.org/abs/2405.15325 https://mastoxiv.page/@arXiv_csLG_bot/112511890051553111
- Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra
https://arxiv.org/abs/2405.15877 https://mastoxiv.page/@arXiv_csLG_bot/112517547424098076
- Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric
Yan Shvartzshnaider, Vasisht Duddu
https://arxiv.org/abs/2409.03735 https://mastoxiv.page/@arXiv_csLG_bot/113089789682783135
- Low-Rank Filtering and Smoothing for Sequential Deep Learning
Joanna Sliwa, Frank Schneider, Nathanael Bosch, Agustinus Kristiadi, Philipp Hennig
https://arxiv.org/abs/2410.06800 https://mastoxiv.page/@arXiv_csLG_bot/113283021321510736
- Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Xiaoyu Tao, Tingyue Pan, Mingyue Cheng, Yucong Luo, Qi Liu, Enhong Chen
https://arxiv.org/abs/2410.18686 https://mastoxiv.page/@arXiv_csLG_bot/113367101100828901
- Fairness via Independence: A (Conditional) Distance Covariance Framework
Ruifan Huang, Haixia Liu
https://arxiv.org/abs/2412.00720 https://mastoxiv.page/@arXiv_csLG_bot/113587817648503815
- Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
Simon Frieder, et al.
https://arxiv.org/abs/2412.15184 https://mastoxiv.page/@arXiv_csLG_bot/113683924322164777
- Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy
Ishank Juneja, Carlee Joe-Wong, Osman Ya\u{g}an
https://arxiv.org/abs/2501.10290 https://mastoxiv.page/@arXiv_csLG_bot/113859392622871057
- Towards Human-Guided, Data-Centric LLM Co-Pilots
Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat, Anders Boyd, Mihaela van der Schaar
https://arxiv.org/abs/2501.10321 https://mastoxiv.page/@arXiv_csLG_bot/113859392688054204
- Regularized Langevin Dynamics for Combinatorial Optimization
Shengyu Feng, Yiming Yang
https://arxiv.org/abs/2502.00277
- Generating Samples to Probe Trained Models
Eren Mehmet K{\i}ral, Nur\c{s}en Ayd{\i}n, \c{S}. \.Ilker Birbil
https://arxiv.org/abs/2502.06658 https://mastoxiv.page/@arXiv_csLG_bot/113984059089245671
- On Agnostic PAC Learning in the Small Error Regime
Julian Asilis, Mikael M{\o}ller H{\o}gsgaard, Grigoris Velegkas
https://arxiv.org/abs/2502.09496 https://mastoxiv.page/@arXiv_csLG_bot/114000974082372598
- Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo, Yongxu Zhu, Geoffrey Ye Li
https://arxiv.org/abs/2502.10784 https://mastoxiv.page/@arXiv_csLG_bot/114023667639951005
- On the Effect of Sampling Diversity in Scaling LLM Inference
Wang, Liu, Chen, Light, Liu, Chen, Zhang, Cheng
https://arxiv.org/abs/2502.11027 https://mastoxiv.page/@arXiv_csLG_bot/114023688225233656
- How to use score-based diffusion in earth system science: A satellite nowcasting example
Randy J. Chase, Katherine Haynes, Lander Ver Hoef, Imme Ebert-Uphoff
https://arxiv.org/abs/2505.10432 https://mastoxiv.page/@arXiv_csLG_bot/114516300594057680
- PEAR: Equal Area Weather Forecasting on the Sphere
Hampus Linander, Christoffer Petersson, Daniel Persson, Jan E. Gerken
https://arxiv.org/abs/2505.17720 https://mastoxiv.page/@arXiv_csLG_bot/114572963019603744
- Train Sparse Autoencoders Efficiently by Utilizing Features Correlation
Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev, Daniil Gavrilov, Nikita Balagansky
https://arxiv.org/abs/2505.22255 https://mastoxiv.page/@arXiv_csLG_bot/114589956040892075
- A Certified Unlearning Approach without Access to Source Data
Umit Yigit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury, Basak Guler
https://arxiv.org/abs/2506.06486 https://mastoxiv.page/@arXiv_csLG_bot/114658421178857085
toXiv_bot_toot

Series D, Episode 11 - Orbit
SERVALAN: I hope so, Egrorian. I've waited a long time for this.
EGRORIAN: His death is a mathematical certainty. The product of a simple equation.
https://blake.torpidity.net/m/411/202 B7B6

Good work if you can get it: Elon Musk is set to make more than every elementary school teacher COMBINED (Katie Hawkinson/The Independent)
https://www.independent.co.uk/news/world/americas/us-politics/elon-musk-tesla-pay-package-earnings-b2867752.html
http://www.memeorandum.com/251118/p163#a251118p163

Actually, I do want to come back to masculinity under patriarchy and whiteness under white supremacy because I think it's worth talking more about. The "man" under patriarchy (at least "Western" patriarchy) is represented as power and independence. The man needs nothing and thus owes nothing to anyone. The man controls and is not controlled, which is intimately related to independence as dependence can make someone vulnerable to control. The image of "man" projects power and invulnerability. At the same time "man" is a bumbling fool who can't be held accountable for his inability to control his sexual urges. He must be fed and cared for, as though another child. His worst behaviors must be dismissed with phrases such as "boys will be boys" and "locker room talk." The absurdity of the concept of human "independence" is impossible to understate.
Even if you go all Ted Kaczynski, you have still been raised and taught. This is, perhaps, why it is so much more useful to think in terms of obligations than rights. Rights can be claimed and protected with violence alone, but obligations reveal the true interdependence that sustains us. A "man" may assert his rights. Yet, on some level, we all know that the "man" of patriarchy acts as a child who is not mature enough to recognize his obligations.
White violence and white fragility reflect the same dichotomy. "The master race" somehow always needs brown folks to make all their shit and do all the reproductive labor for them. For those who fully embrace whiteness, the "safe space" is a joke. DEI shows weakness. Yet, when presented with an honest history adults become children who are incapable of differentiating between criticism and simple facts. *They* become the ones who must be kept safe. The expectation to be responsible for one's own words and actions, one of the very core definitions of being an adult, is far too much to expect. Their guilt needs room, needs tending, needs caring. White people cannot simply "grow the fuck up" or, as they may say of slavery, "fucking get over it."
And again, interestingly, it is *rights* that they reference: "Mah Freeze PEACH!" I find it hard to distinguish between such and my own child's assertion that anything she doesn't like is "not fair!" No, these assertions fail to recognize the fundamental fabric of adult society: the obligations we hold to each other.
At the intersection of all privilege is the sovereign, the ultimate god-man-baby. Again, referencing the essay (https://hexmhell.writeas.com/observations-on-domination-and-trump)
> This is where it becomes important to consider the ideology behind the sovereign ritual. Participation within the sovereign ritual denotes to the participants elements of the sovereign. That is, all agents of the sovereign are, essentially, micro dictators. By carrying out the will of the sovereign, these micro dictators can, by extension, act outside of the law.
While law enforcement is the ultimate representative of sovereign violence, privileges allow a gradated approximation of the sovereign. Those who are "closer" in privilege to the sovereign may, for example, be permitted to carry out violence against those who are father away. The gradation of privilege turns the whole society, except for the least privileged, into a cult that protects the privilege system on behalf of the most privileged. (And immediately Malcolm X pops to mind as having already talked about part of this relationship in 1963 https://www.youtube.com/watch?v=jf7rsCAfQCo.)

Series B, Episode 08 - Hostage
JENNA: What?
CALLY: I don't believe it.
MOLOK: Show me the ship; I must learn about it.
CALLY: You're a crimo, aren't you?
https://blake.torpidity.net/m/208/582 B7B5

CBS has cut two streaming shows, disbanded its race and culture unit, eliminated the Johannesburg bureau; all eight on-air correspondents cut were women (Justin Baragona/The Independent)
https://www.independent.co.uk/news/world/americas/cbs-news-l…

CBS News fired 8 on-air personalities in latest layoffs under new leader Bari Weiss. All of them are women
EXCLUSIVE: Multiple sources told The Independent that senior foreign correspondent Debora Patta was added to the layoff list following a last-minute change by editor-in-chief Bari Weiss.

Putin insists certain elements of Trump’s peace plan to end Ukraine war are unacceptable | The Independent
https://www.independent.co.uk/news/world/europe/russia-putin-trump-ukraine-peace-plan-b2878544.html

Implication Problems over Positive Semirings
Minna Hirvonen
https://arxiv.org/abs/2510.08112 https://arxiv.org/pdf/2510.08112

Implication Problems over Positive Semirings
We study various notions of dependency in semiring team semantics. Semiring teams are essentially database relations, where each tuple is annotated with some element from a positive semiring. We consider semiring generalizations of several dependency notions from database theory and probability theory, including functional and inclusion dependencies, marginal identity, and (probabilistic) independence. We examine axiomatizations of implication problems, which are rule-based characterizations fo…

Free Independence is not Definable
William Boulanger, Jakub Curda, Emma Harvey, Yizhi Li, Jennifer Pi
https://arxiv.org/abs/2510.04836 https://arxiv.org/pd…

Free Independence is not Definable
Free independence is an important tool for studying the structure of operator algebras. It is natural to ask from the model-theoretic standpoint whether free independence is captured well in first-order model theory via the notion of a definable set. We prove that pairs of freely independent elements do not form a definable set in the sense of continuous model theory, relative to the theory of both C$^*$-probability spaces and tracial von Neumann algebras.

Series B, Episode 04 - Horizon
[Teleport section]
AVON: [Snapping on a bracelet] What do these detectors look like?
ORAC: Logic would suggest they are camouflaged - in plants.
https://blake.torpidity.net/m/204/536 B7B3