Show threadFabrizio MusacchioMay 5

Following up on this, I also explored a more direct use of #WassersteinDistance in #WGANs: Instead of training a discriminator, the generator is optimized by explicitly computing the #OptimalTransport distance between real and generated samples. This turns the loss into the actual metric of interest and removes the adversarial setup, leading to a more direct and stable training signal. And we can generate cool animations, too ^_^

🌍 https://www.fabriziomusacchio.com/blog/2023-07-30-wgan_with_direct_wasserstein_distance/

#MachineLearning #Wasserstein

Show threadFabrizio MusacchioMay 5

I actually wrote a short introduction to #WassersteinDistance and #OptimalTransport some time ago, if you’re looking for a more intuitive entry point:

🌍 https://www.fabriziomusacchio.com/blog/2023-07-23-wasserstein_distance/

#Wasserstein

Fabrizio MusacchioMay 4

📐📚New study on #WassersteinDistance: Bonet et al. study #geodesic rays in #Wasserstein space and derive conditions for their existence. They show that #Busemann functions can be computed via #OT, with closed-form solutions for 1D and Gaussian cases. This enables efficient sliced distances for labeled datasets, closely matching classical metrics at lower cost and supporting dataset “flows” for #TransferLearning.

🌍 https://openreview.net/forum?id=Xpt0HEC3fO

#OptimalTransport #MachineLearning

Fabrizio MusacchioApr 7

📐 New preprint by Gabriel Peyré: The paper introduces a new class of spectral #Wasserstein distances, linking #OptimalTransport with normalized #gradient methods. It shows that spectrally normalized #GradientDescent can be interpreted as a gradient flow in this spectral-W geometry, providing a principled bridge between #optimization dynamics and transport metrics:

📄 https://arxiv.org/abs/2604.04891

#MachineLearning #WassersteinDistance

 JetstreamApr 7

米Google ストア「Wasserstein オンザゴー充電器 Google Pixel Watch 4」発売
https://jetstream.blog/2026/04/07/us-google-store-wasserstein-onthego-charger-pixel-watch-4/

#jetstream_blog #発売情報 #Google_Pixel_Watch_4 #Google_ストア #Made_for_Google #Wasserstein

米Google ストア「Wasserstein オンザゴー充電器 Google Pixel Watch 4」発売

「Wasserstein On-the-Go Charger for Google Pixel Watch 4（41mm & 45mm）」が、2026 年 3 月下旬から 2026 年 4 月上旬にかけて、米国の Google 公式 EC サイト「Google ストア」で発売。米国「Google ストア」での価格は $28.99 で、2026 年 4 月上旬時点では在庫切れ。そのうち日本にも投入されるかも。

Jetstream
Freya BlekmanMar 15
This #CMSPaper investigates different #AI #machinelearning methods that aim to find jets that are inconsistent with the standard model. It shows that a new method called #Wasserstein normalized autoencodes works much better than other neural networks arxiv.org/abs/2510.02168
 JetstreamMar 2

国内Amazon登場！「Google Pixel Watch 4」Wassersteinポータブル充電器
https://jetstream.blog/2026/03/03/made-for-google-wasserstein-pixel-watch-4-charger-amazon-jp/

#jetstream_blog #Android情報 #Amazon #Amazon_co_jp #Google_Pixel_Watch_4 #Made_for_Google #Wasserstein

国内Amazon登場！「Google Pixel Watch 4」Wassersteinポータブル充電器

「Google Pixel Watch 4」用の、「Made for Google」認定充電アダプタ「Wasserstein On-the-Go Charger for Google Pixel Watch 4（41mm & 45mm）」が、日本国内の Amazon.co.jp に登場。「Wasserstein オンザゴー充電器 Google Pixel Watch 4（41mm & 45mm）対応 - ポータブル充電ドック」。まだ予約も開始されておらず、価格も未公開。

Jetstream
Freya BlekmanFeb 13
This #CMSPaper investigates different #AI #machinelearning methods that aim to find jets that are inconsistent with the standard model. It shows that a new method called #Wasserstein normalized autoencodes works much better than other neural networks arxiv.org/abs/2510.02168
Freya BlekmanFeb 2
This #CMSPaper investigates different #AI #machinelearning methods that aim to find jets that are inconsistent with the standard model. It shows that a new method called #Wasserstein normalized autoencodes works much better than other neural networks arxiv.org/abs/2510.02168
Freya BlekmanJan 21
This #CMSPaper investigates different #AI #machinelearning methods that aim to find jets that are inconsistent with the standard model. It shows that a new method called #Wasserstein normalized autoencodes works much better than other neural networks arxiv.org/abs/2510.02168