#Development #Guides
Beyond CSS ‘border-radius’ · What the new ‘corner-shape’ delivers to everyday UIs https://ilo.im/16bc4i

_____
#ModernCSS #Cards #Buttons #Batches #Tags #ProgressiveEnhancement #Browsers #WebDev #Frontend #CSS

Beyond border-radius: What The CSS corner-shape Property Unlocks For Everyday UI — Smashing Magazine

For years, developers have been hacking around the limitations of `border-radius`, using clip-path, SVG masks, and fragile workarounds just to get anything other than round corners. The new `corner-shape` property finally changes that, opening the door to beveled, scooped, and squircle corners.

Smashing Magazine
Reliable Immutable Transfer Protocol

an incredibly simple protocol for reliably and correctly downloading large immutable files. (this is a follow-up and successor to my RTP...

binarycat

'Fast Rates in Pool-Based Batch Active Learning', by Claudio Gentile, Zhilei Wang, Tong Zhang.

http://jmlr.org/papers/v25/22-1409.html

#labeling #batches #batch

Fast Rates in Pool-Based Batch Active Learning

'Law of Large Numbers and Central Limit Theorem for Wide Two-layer Neural Networks: The Mini-Batch and Noisy Case', by Arnaud Descours, Arnaud Guillin, Manon Michel, Boris Nectoux.

http://jmlr.org/papers/v25/22-0952.html

#asymptotic #stochastic #batches

Law of Large Numbers and Central Limit Theorem for Wide Two-layer Neural Networks: The Mini-Batch and Noisy Case

Black-Box Batch Active Learning for Regression

Andreas Kirsch

Action editor: Ying Nian Wu.

https://openreview.net/forum?id=fvEvDlKko6

#regression #batches #batch

Black-Box Batch Active Learning for Regression

Batch active learning is a popular approach for efficiently training machine learning models on large, initially unlabelled datasets by repeatedly acquiring labels for batches of data points....

OpenReview

U-Statistics for Importance-Weighted Variational Inference

Javier Burroni, Kenta Takatsu, Justin Domke, Daniel Sheldon

https://openreview.net/forum?id=oXmwAPlbVw

#variational #batches #inference

U-Statistics for Importance-Weighted Variational Inference

We propose the use of U-statistics to reduce variance for gradient estimation in importance-weighted variational inference. The key observation is that, given a base gradient estimator that...

OpenReview

EVIDENCE-BASED ELECTIONS:
CREATE A MEANINGFUL PAPER TRAIL, THEN AUDIT

https://www.cs.princeton.edu/~appel/papers/Appel-Stark-GLTR-2020.pdf

#batches #percentile #Princeton