Tootfinder

LightGTS: A Lightweight General Time Series Forecasting Model
Yihang Wang, Yuying Qiu, Peng Chen, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo
https://arxiv.org/abs/2506.06005

LightGTS: A Lightweight General Time Series Forecasting Model
Existing works on general time series forecasting build foundation models with heavy model parameters through large-scale multi-source pre-training. These models achieve superior generalization ability across various datasets at the cost of significant computational burdens and limitations in resource-constrained scenarios. This paper introduces LightGTS, a lightweight general time series forecasting model designed from the perspective of consistent periodical modeling. To handle diverse scales…

Attorney General Bonta, Governor Newsom Challenge Trump Order Seeking to Federalize California National Guard (State of California)
https://oag.ca.gov/news/press-releases/attorney-general-bonta-governor-newsom-challenge-trump-order-seeking-federalize
http://www.memeorandum.com/250609/p96#a250609p96

On the completeness of the $\delta_{KLS}$-generalized statistical field theory
P. R. S. Carvalho
https://arxiv.org/abs/2506.05537 https://

On the completeness of the $δ_{KLS}$-generalized statistical field theory
In this work we introduce a field-theoretic tool that enable us to evaluate the critical exponents of $δ_{KLS}$-generalized systems undergoing continuous phase transitions, namely $δ_{KLS}$-generalized statistical field theory. It generalizes the standard Boltzmann-Gibbs through the introduction of the $δ_{KLS}$ parameter from which Boltzmann-Gibbs statistics is recovered in the limit $δ_{KLS}\rightarrow 0$. From the results for the critical exponents we provide the referred physical interp…

This https://arxiv.org/abs/2409.08826 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Generalized Nearest Neighbor Decoding: General Input Constellation and a Case Study of Interference Suppression
In this work, generalized nearest neighbor decoding (GNND), a recently proposed receiver architecture, is studied for channels under general input constellations, and multiuser uplink interference suppression is employed as a case study for demonstrating its potential. In essence, GNND generalizes the well-known nearest neighbor decoding, by introducing a symbol-level memoryless processing step, which can be rendered seamlessly compatible with Gaussian channel-based decoders. First, criteria of…

Generalized measurements for Bell tests in different probability spaces
Alfredo Luis
https://arxiv.org/abs/2506.07496 https://arxiv.o…

Generalized measurements for Bell tests in different probability spaces
Bell tests are of profound statistical nature. Besides physical considerations, the proper understanding of their implications should involve detailed statistical analyses. In this regard, recent works have shown that their consequences and interpretations depend on the probability space adopted. Some other recent works have also shown that generalized measurements may allow to further exploit the statistics of Bell-like tests. Following these ideas, in this work we show that one and the same e…

A general model for time-minimizing navigation on a mountain slope under gravity
Nicoleta Aldea, Piotr Kopacz
https://arxiv.org/abs/2506.06720 https://

A general model for time-minimizing navigation on a mountain slope under gravity
In this work, we solve the generalized Matsumoto's slope-of-a-mountain problem by means of Riemann-Finsler geometry, making close links with the Zermelo navigation problem. The time-minimizing navigation under gravity is analyzed in the general model of a slippery mountain slope being a Riemannian manifold. Both the transverse and longitudinal gravity-additives with respect to the direction of motion are admitted to vary simultaneously in the full ranges, showing the impact of cross- and along-…

Lagrangian-based Equilibrium Propagation: generalisation to arbitrary boundary conditions & equivalence with Hamiltonian Echo Learning
Guillaume Pourcel, Debabrota Basu, Maxence Ernoult, Aditya Gilra
https://arxiv.org/abs/2506.06248

Lagrangian-based Equilibrium Propagation: generalisation to arbitrary boundary conditions & equivalence with Hamiltonian Echo Learning
Equilibrium Propagation (EP) is a learning algorithm for training Energy-based Models (EBMs) on static inputs which leverages the variational description of their fixed points. Extending EP to time-varying inputs is a challenging problem, as the variational description must apply to the entire system trajectory rather than just fixed points, and careful consideration of boundary conditions becomes essential. In this work, we present Generalized Lagrangian Equilibrium Propagation (GLEP), which e…

Democrats accuse Gabbard of illegal interference in IG office (Washington Post)
https://www.washingtonpost.com/national-security/2025/06/09/gabbard-inspector-general-democrats-illegal/
http://www.memeorandum.com/250609/p155#a250609p155

A Concurrent Generalized Kropina Change
A. Soleiman, Ebtsam H. Taha
https://arxiv.org/abs/2506.06000 https://arxiv.org/pdf/2506.06000…

A Concurrent Generalized Kropina Change
This paper investigates a generalized Kropina metric featuring a specific $π$-form. Start with a Finsler manifold $(M,F)$ admits a concurrent $π$-vector field $\overlineφ$, then, examine the $ϕ$-concurrent generalized Kropina change defined by $\widehat{F}=\frac{F^{m+1}}{Φ^{m}}$, where $Φ$ represents the corresponding $1$-form. We investigate the fundamental geometric objects associated with $\widehat{F}$ in an intrinsic manner after adopting this modification and present an example of a …

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
Muhammed Ustaomeroglu, Guannan Qu
https://arxiv.org/abs/2506.06179

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in multi-agent reinforcement learning to alleles in genetic sequences, and show that a single layer linear self-attention can efficiently represent, learn, and generalize functions capturing pairwise interactions, including out-of-distribution scenarios. Our analysis r…