#Orthogonalisation
LightNews LightNews
florianbonet.bsky.social
Un #filtremodal situé au cœur d'un secteur touristique d'#Amsterdam. Il permet d'autoriser uniquement certains mouvements de véhicules, là où tous les mouvements piétons et cyclistes sont permis. Orthogonalisation des conflits avec le #tramway.
March 16, 2026 at 9:14 PM
axolotlpillow.bsky.social
falsification uhh identity orthogonalisation uhhhhhh
September 4, 2026 at 10:07 AM
meatflavourdev.bsky.social
mlabonne.github.io/blog/posts/2...

Removing the model’s built-in refusal mechanism, allowing it to respond to all types of prompts.

“Abliteration” can uncensor any LLM without retraining
Abliteration with weight orthogonalisation
July 8, 2025 at 10:13 AM
research.migraine.kr
Dynamic connectivity was estimated using amplitude envelope correlation, with symmetric orthogonalisation to reduce leakage. Edge-centric functional connectivity was calculated from co-fluctuation time series across frequency bands. (🧵 5/14)
June 11, 2026 at 10:51 AM
purble.bsky.social
There are two principle problems with this: the sub-space generally varies with time and not necessarily slowly; and such genders are not generally orthonormal and previous attempts at orthogonalisation have had mixed to negative results.
July 7, 2025 at 8:02 PM
timhenke.bsky.social
In my head I thought there was a really cute proof of the Cauchy-Schwarz inequality

Something like taking a clever inner product v + w and v - w and using non-negativity

But I can't find it. The only proofs I saw used uglier tricks like orthogonalisation or taking the discriminant of a polynomial
September 27, 2024 at 5:44 PM
timhenke.bsky.social
yeah, this was basically the proof on wikipedia, but there it was equivalently done via the discriminant of the quadratic

Still I have some vague memory of it being possible without the polynomial or without the orthogonalisation, but it's possible I'm confusing it with a different inequality
September 27, 2024 at 5:58 PM
paperposterbot.bsky.social
arXiv📈🤖
Design-Robust Event-Study Estimation under Staggered Adoption Diagnostics, Sensitivity, and Orthogonalisation
By Wright
This paper develops a design-first econometric framework for event-study and difference-in-differences estimands under staggered adoption with heterogeneous effects, emphasising (i) exact probability limits for conventional two-way fixed effects event-study regressions, (ii) computable design diagnostics that quantify contamination and negative-weight risk, and (iii) sensitivity-robust inference that remains uniformly valid under restricted violations of parallel trends. The approach is accompanied by orthogonal score constructions that reduce bias from high-dimensional nuisance estimation when conditioning on covariates. Theoretical results and Monte Carlo experiments jointly deliver a self-contained methodology paper suitable for finance and econometrics applications where timing variation is intrinsic to policy, regulation, and market-structure changes.
January 28, 2026 at 4:12 PM
timhenke.bsky.social
Yeah, I think this is the idea of orthogonalisation. Write w = u + z where* <v,z> = 0 and u = a*v. Then

||v||^2 ||w||^2 = ||v||^2 * (||u||^2 + ||z||^2) > |a|^2*||v||^4 = |a|^2*|<v,v>|^2 = |<v,u>|^2

*we can guarantee this by choosing u = <v,w>/<v,v> * v and z = w - u
September 27, 2024 at 6:22 PM
paperposterbot.bsky.social
arXiv📈🤖
Orthogonal polynomials on path-space
By Chevyrev, Ferrucci, Lee et al
We consider the orthogonalisation of the signature of a stochastic process as the analogue of orthogonal polynomials on path-space. Under an infinite radius of convergence assumption, we prove density of linear functions on the signature in $L^p$ functions on grouplike elements, making it possible to represent a square-integrable function on (rough) paths as an $L^2$-convergent series. By viewing the shuffle algebra as commutative polynomials on the free Lie algebra, we revisit much of the theory of classical orthogonal polynomials in several variables, such as the recurrence relation and Favard's theorem. Finally, we restrict our attention to the case of Brownian motion with and without drift, and prove that dimension-independent orthogonal signature exists with drift but not without. We end with numerical examples of how orthogonal signature polynomials of Brownian motion can be applied for the approximation of functions on paths sampled from the Wiener measure.
February 24, 2026 at 9:39 PM
paperposterbot.bsky.social
arXiv📈🤖
Orthogonal polynomials on path-space
By Chevyrev, Ferrucci, Lee et al
We consider the orthogonalisation of the signature of a stochastic process as the analogue of orthogonal polynomials on path-space. Under an infinite radius of convergence assumption, we prove density of linear functions on the signature in $L^p$ functions on grouplike elements, making it possible to represent a square-integrable function on (rough) paths as an $L^2$-convergent series. By viewing the shuffle algebra as commutative polynomials on the free Lie algebra, we revisit much of the theory of classical orthogonal polynomials in several variables, such as the recurrence relation and Favard's theorem. Finally, we restrict our attention to the case of Brownian motion with and without drift, and prove that dimension-independent orthogonal signature exists with drift but not without. We end with numerical examples of how orthogonal signature polynomials of Brownian motion can be applied for the approximation of functions on paths sampled from the Wiener measure.
February 24, 2026 at 6:36 PM
paperposterbot.bsky.social
arXiv📈🤖
Design-Robust Event-Study Estimation under Staggered Adoption Diagnostics, Sensitivity, and Orthogonalisation
By Wright
This paper develops a design-first econometric framework for event-study and difference-in-differences estimands under staggered adoption with heterogeneous effects, emphasising (i) exact probability limits for conventional two-way fixed effects event-study regressions, (ii) computable design diagnostics that quantify contamination and negative-weight risk, and (iii) sensitivity-robust inference that remains uniformly valid under restricted violations of parallel trends. The approach is accompanied by orthogonal score constructions that reduce bias from high-dimensional nuisance estimation when conditioning on covariates. Theoretical results and Monte Carlo experiments jointly deliver a self-contained methodology paper suitable for finance and econometrics applications where timing variation is intrinsic to policy, regulation, and market-structure changes.
January 28, 2026 at 10:09 PM
paperposterbot.bsky.social
arXiv📈🤖
Design-Robust Event-Study Estimation under Staggered Adoption Diagnostics, Sensitivity, and Orthogonalisation
By Wright
This paper develops a design-first econometric framework for event-study and difference-in-differences estimands under staggered adoption with heterogeneous effects, emphasising (i) exact probability limits for conventional two-way fixed effects event-study regressions, (ii) computable design diagnostics that quantify contamination and negative-weight risk, and (iii) sensitivity-robust inference that remains uniformly valid under restricted violations of parallel trends. The approach is accompanied by orthogonal score constructions that reduce bias from high-dimensional nuisance estimation when conditioning on covariates. Theoretical results and Monte Carlo experiments jointly deliver a self-contained methodology paper suitable for finance and econometrics applications where timing variation is intrinsic to policy, regulation, and market-structure changes.
January 28, 2026 at 7:10 PM
repec-nep-ecm.bsky.social
Design-Robust Event-Study Estimation under Staggered Adoption Diagnostics, Sensitivity, and Orthogonalisation: Craig S Wright
NEP/RePEc link
to paper
d.repec.org
February 7, 2026 at 5:51 AM
arxiv-econ-gn.bsky.social
Design-Robust Event-Study Estimation under Staggered Adoption Diagnostics, Sensitivity, and Orthogonalisation
https://arxiv.org/abs/2601.18801
January 28, 2026 at 5:52 AM
mathgr-bot.bsky.social
arXiv:2505.16295v1 Announce Type: new
Abstract: In 1976, L.N. Vaserstein used a construction analogous to the Gram-Schmidt orthogonalisation, for obtaining a set of symplectic matrices from a set of elementary matrices. We have a similar construction [1/2 of https://arxiv.org/abs/2505.16295v1]
May 23, 2025 at 6:03 AM
quantph-bot.bsky.social
Matisse Wei-Yuan Tu, Angel Rubio, E. K. U. Gross: Nuclear interference by electronic de-orthogonalisation https://arxiv.org/abs/2603.02966 https://arxiv.org/pdf/2603.02966 https://arxiv.org/html/2603.02966
March 4, 2026 at 6:51 AM
krxiv-quant-ph.bsky.social
Nuclear interference by electronic de-orthogonalisation
https://arxiv.org/pdf/2603.02966
Matisse Wei-Yuan Tu, Angel Rubio, E.K.U. Gross.
https://arxiv.org/abs/2603.02966
arXiv abstract link
arxiv.org
March 4, 2026 at 4:34 AM
orthogonal-is-me.bsky.social
C'est magnifique!

Le cerveau américain ne peut pas comprendre.

#Orthogonalisation
#Amsterdam
#Amstertram
March 16, 2026 at 10:48 PM
rhens.bsky.social
4.1 Topics covered: Experimental vs Field Designs, Multiple Regression, Correlated Predictors, Range effects, Measurement noise, Sequential Orthogonalisation (Type II vs Type III sum of squares)
January 23, 2026 at 2:44 PM
zbmathopen.bsky.social
Jørgen Pedersen Gram zbmath.org/authors/gram..., famous for the Gram-Schmidt orthogonalisation, was #botd 175 years ago. "Note sur les zéros de la fonction ζ(𝘴) de Riemann" was reviewed in zbmath.org/34.0461.01.
Jørgen Pedersen Gram - Author Profile - zbMATH Open
zbmath.org
June 27, 2025 at 9:56 PM
econem-bot.bsky.social
Craig S Wright: Design-Robust Event-Study Estimation under Staggered Adoption Diagnostics, Sensitivity, and Orthogonalisation https://arxiv.org/abs/2601.18801 https://arxiv.org/pdf/2601.18801 https://arxiv.org/html/2601.18801
January 28, 2026 at 6:35 AM