Random Projections
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era
arXiv:2510.04127v2 Announce Type: replace Abstract: Approximate nearest neighbour (ANN) search underpins large-scale retrieval, increasingly within the retrieval-augmented generation pipelines that ground large language models, yet the methods that address it have multiplied across communities until they are seldom read as a single field. We argue they form one field with three design choices, and develop the projection-quantisation-organisation (PQO) lens, under which locality-sensitive...
Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes
arXiv:2601.20076v2 Announce Type: replace-cross Abstract: We consider minimizing an objective function subject to constraints defined by the intersection of lower-level sets of convex functions. We study two cases: (i) strongly convex and Lipschitz-smooth objective function and (ii) convex but possibly nonsmooth objective function. To deal with the constraints that are not easy to project on, we use a randomized feasibility algorithm with Polyak steps and a random number of sampled...
Bagged Polynomial Regression and Neural Networks
arXiv:2205.08609v3 Announce Type: replace-cross Abstract: Climate and environmental applications increasingly rely on high-dimensional prediction from remote sensing and other scientific data. Neural networks (NN) can deliver strong accuracy in these settings, but they are often hard to audit and hard to align with domain knowledge. As an alternative, we propose bagged polynomial regression with random projections (BPR), an econometrics-native ensemble that averages many regularized...
Flood of AI 'garbage' is pushing open-source developers to the limit
A viral cartoon about open-source software shows a teetering pile of boxes labelled “all modern digital infrastructure” and one tiny box right at the bottom, propping up the whole lot: “a project some random person in Nebraska has been thanklessly maintaining since 2003”. That’s the reality of open source: every website, application and operating system relies on it. Modern society couldn’t function without it, and yet it’s written by volunteers in their spare time.
Two Datasets Are Better Than One: Method of Double Moments for 3-D Reconstruction in Cryo-EM
Announce Type: replace Abstract: Cryo-electron microscopy (cryo-EM) is a powerful imaging technique for reconstructing three-dimensional molecular structures from noisy tomographic projection images of randomly oriented particles. We introduce a new data fusion framework, termed the method of double moments (MoDM), which reconstructs molecular structures from two instances of the second-order moment of projection images obtained under distinct orientation distributions: one uniform, the...
An Upper Bound on Grothendieck's Constant
Announce Type: cross Abstract: We show that Grothendieck's real constant $K_G$ can be upper bounded by projecting vectors onto a random plane through the origin and thresholding a degree five Hermite polynomial. This resolves a conjecture of Braverman-Makarychev-Makarychev-Naor from 2011, who required an extra randomization step in their rounding scheme and proved $K_G<\frac{\pi}{2\log(1+\sqrt{2})}-10^{-500}$. As a corollary of our result, we prove the bound...
KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models
new Abstract: Vision-language foundation models such as CLIP and SigLIP provide widely used representations for multimodal learning systems. While these models are typically compared through downstream performance, such evaluations often do not explain how their representations differ structurally. In this work, we study this problem through the task of Contrastive Embedding Clustering: identifying sample subsets that are weakly clustered under one representation but strongly clustered under...
Dimensionality Reduction for Robust Federated Learning: A Theoretical Analysis and Convergence Guarantee
arXiv:2605.28335v2 Announce Type: replace Abstract: Federated Learning (FL) enables multiple clients to collaboratively train models without sharing raw data, but it is highly vulnerable to Byzantine attacks. Existing robust approaches can neutralize these threats but incur substantial computational overhead during high-dimensional gradient aggregation, an overhead that scales poorly with model size and increasingly dominates the training cost as modern models grow larger. To address this...
The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders
arXiv:2606.07882v1 Announce Type: new Abstract: Different vision neural networks -- trained to classify, contrast, reconstruct, or match images to text -- should have correspondingly different internal representations. We report that they do not.
Beyond Compression: Quantifying Spectral Accessibility in Vision Representations
Announce Type: new Abstract: Vision-language models map visual features into a shared embedding space through learned projection layers, yet it remains unclear how these transformations alter the structure of visual information. This study examines changes in representation through spatial-frequency accessibility, measured by the linear recoverability of band-limited Fourier energy from model representations. To isolate effects beyond dimensionality reduction, we introduce Residual Spectral...