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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Ryota Tomioka

Ryota Tomioka

University of Tokyo

DistIR: An Intermediate Representation and Simulator for Efficient Neural Network Distribution


Nov 09, 2021
Keshav Santhanam, Siddharth Krishna, Ryota Tomioka, Tim Harris, Matei Zaharia


  Access Paper or Ask Questions

An Information-theoretic Approach to Distribution Shifts


Jun 07, 2021
Marco Federici, Ryota Tomioka, Patrick Forré


  Access Paper or Ask Questions

Regularized Policies are Reward Robust


Jan 18, 2021
Hisham Husain, Kamil Ciosek, Ryota Tomioka


  Access Paper or Ask Questions

On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them


Jun 15, 2020
Chen Liu, Mathieu Salzmann, Tao Lin, Ryota Tomioka, Sabine Süsstrunk


  Access Paper or Ask Questions

On Certifying Non-uniform Bound against Adversarial Attacks


Mar 15, 2019
Chen Liu, Ryota Tomioka, Volkan Cevher


  Access Paper or Ask Questions

Hierarchical Representations with Poincaré Variational Auto-Encoders


Jan 17, 2019
Emile Mathieu, Charline Le Lan, Chris J. Maddison, Ryota Tomioka, Yee Whye Teh


  Access Paper or Ask Questions

Depth and nonlinearity induce implicit exploration for RL


May 29, 2018
Justas Dauparas, Ryota Tomioka, Katja Hofmann


  Access Paper or Ask Questions

QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding


Dec 06, 2017
Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, Milan Vojnovic


  Access Paper or Ask Questions

AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks


Jun 22, 2017
Alexander L. Gaunt, Matthew A. Johnson, Maik Riechert, Daniel Tarlow, Ryota Tomioka, Dimitrios Vytiniotis, Sam Webster

* 17 pages, 13 figures 

  Access Paper or Ask Questions

Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations


May 24, 2017
Diane Bouchacourt, Ryota Tomioka, Sebastian Nowozin


  Access Paper or Ask Questions

Geometry of Optimization and Implicit Regularization in Deep Learning


May 08, 2017
Behnam Neyshabur, Ryota Tomioka, Ruslan Salakhutdinov, Nathan Srebro

* This survey chapter was done as a part of Intel Collaborative Research institute for Computational Intelligence (ICRI-CI) "Why & When Deep Learning works -- looking inside Deep Learning" compendium with the generous support of ICRI-CI. arXiv admin note: substantial text overlap with arXiv:1506.02617 

  Access Paper or Ask Questions

Gaussian Attention Model and Its Application to Knowledge Base Embedding and Question Answering


Nov 30, 2016
Liwen Zhang, John Winn, Ryota Tomioka

* 16 pages, 4 figures 

  Access Paper or Ask Questions

f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization


Jun 02, 2016
Sebastian Nowozin, Botond Cseke, Ryota Tomioka

* 17 pages 

  Access Paper or Ask Questions

Data-Dependent Path Normalization in Neural Networks


Jan 19, 2016
Behnam Neyshabur, Ryota Tomioka, Ruslan Salakhutdinov, Nathan Srebro

* 17 pages, 3 figures 

  Access Paper or Ask Questions

Interpolating Convex and Non-Convex Tensor Decompositions via the Subspace Norm


Oct 27, 2015
Qinqing Zheng, Ryota Tomioka


  Access Paper or Ask Questions

Jointly Learning Multiple Measures of Similarities from Triplet Comparisons


Oct 06, 2015
Liwen Zhang, Subhransu Maji, Ryota Tomioka


  Access Paper or Ask Questions

Theoretical and Experimental Analyses of Tensor-Based Regression and Classification


Sep 06, 2015
Kishan Wimalawarne, Ryota Tomioka, Masashi Sugiyama


  Access Paper or Ask Questions

In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning


Apr 16, 2015
Behnam Neyshabur, Ryota Tomioka, Nathan Srebro

* 9 pages, 2 figures 

  Access Paper or Ask Questions

Norm-Based Capacity Control in Neural Networks


Apr 14, 2015
Behnam Neyshabur, Ryota Tomioka, Nathan Srebro

* 29 pages 

  Access Paper or Ask Questions

The Algebraic Combinatorial Approach for Low-Rank Matrix Completion


Aug 19, 2014
Franz J. Király, Louis Theran, Ryota Tomioka

* 37 pages, with an appendix by Takeaki Uno 

  Access Paper or Ask Questions

Spectral norm of random tensors


Jul 07, 2014
Ryota Tomioka, Taiji Suzuki

* 5 pages 

  Access Paper or Ask Questions

Convex Tensor Decomposition via Structured Schatten Norm Regularization


Mar 26, 2013
Ryota Tomioka, Taiji Suzuki

* 12 pages, 3 figures 

  Access Paper or Ask Questions

A Combinatorial Algebraic Approach for the Identifiability of Low-Rank Matrix Completion


Jun 27, 2012
Franz Kiraly, Ryota Tomioka

* Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012) 

  Access Paper or Ask Questions

Discovering Emerging Topics in Social Streams via Link Anomaly Detection


Oct 13, 2011
Toshimitsu Takahashi, Ryota Tomioka, Kenji Yamanishi

* 10 pages, 6 figures 

  Access Paper or Ask Questions

Sharp Convergence Rate and Support Consistency of Multiple Kernel Learning with Sparse and Dense Regularization


Jul 28, 2011
Taiji Suzuki, Ryota Tomioka, Masashi Sugiyama

* 26 pages, 1 figure 

  Access Paper or Ask Questions

Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization


Jul 13, 2011
Taiji Suzuki, Ryota Tomioka, Masashi Sugiyama

* 21 pages, 0 figure 

  Access Paper or Ask Questions

SpicyMKL


May 09, 2011
Taiji Suzuki, Ryota Tomioka

* 30 pages, 6 figures 

  Access Paper or Ask Questions

Regularization Strategies and Empirical Bayesian Learning for MKL


Mar 02, 2011
Ryota Tomioka, Taiji Suzuki

* 19pages, 6 figures 

  Access Paper or Ask Questions

Estimation of low-rank tensors via convex optimization


Mar 02, 2011
Ryota Tomioka, Kohei Hayashi, Hisashi Kashima

* 19 pages, 7 figures 

  Access Paper or Ask Questions

Super-Linear Convergence of Dual Augmented-Lagrangian Algorithm for Sparsity Regularized Estimation


Jan 02, 2011
Ryota Tomioka, Taiji Suzuki, Masashi Sugiyama

* Journal of Machine Learning Research, 12(May):1537-1586, 2011 
* 51 pages, 9 figures 

  Access Paper or Ask Questions