Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Invariance-adapted decomposition and Lasso-type contrastive learning


Oct 13, 2022
Masanori Koyama, Takeru Miyato, Kenji Fukumizu

Add code

* 2022 ICML workshop of Topology, Algebra and Geometry in Machine Learning (spotlight) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Unsupervised Learning of Equivariant Structure from Sequences


Oct 12, 2022
Takeru Miyato, Masanori Koyama, Kenji Fukumizu

Add code

* Accepted to NeurIPS 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Contrastive Representation Learning with Trainable Augmentation Channel


Nov 15, 2021
Masanori Koyama, Kentaro Minami, Takeru Miyato, Yarin Gal

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Out-of-Distribution Generalization with Maximal Invariant Predictor


Aug 04, 2020
Masanori Koyama, Shoichiro Yamaguchi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective


Jul 21, 2020
Ruixiang Zhang, Masanori Koyama, katsuhiko Ishiguro

Add code

* ICML2020 accepted paper 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Meta Learning as Bayes Risk Minimization


Jun 02, 2020
Shin-ichi Maeda, Toshiki Nakanishi, Masanori Koyama

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Reconnaissance and Planning algorithm for constrained MDP


Sep 20, 2019
Shin-ichi Maeda, Hayato Watahiki, Shintarou Okada, Masanori Koyama

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Optuna: A Next-generation Hyperparameter Optimization Framework


Jul 25, 2019
Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, Masanori Koyama

Add code

* 10 pages, Accepted at KDD 2019 Applied Data Science track 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation


May 28, 2019
Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe, Takuya Akiba, Masanori Koyama

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robustness to Adversarial Perturbations in Learning from Incomplete Data


May 24, 2019
Amir Najafi, Shin-ichi Maeda, Masanori Koyama, Takeru Miyato

Add code

* 41 pages, 9 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
>>