Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Optimizing Spatial filters for Robust EEG Single-Trial Analysis

- B. Blankertz, Ryota Tomioka, S. Lemm, M. Kawanabe, K.-R. Muller
- Computer Science
- IEEE Signal Processing Magazine
- 2008

Due to the volume conduction multichannel electroencephalogram (EEG) recordings give a rather blurred image of brain activity. Therefore spatial filters are extremely useful in single-trial analysis… Expand

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

- Sebastian Nowozin, B. Cseke, Ryota Tomioka
- Computer Science, Mathematics
- NIPS
- 2 June 2016

Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution… Expand

QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding

- Dan Alistarh, Demjan Grubic, Jerry Li, Ryota Tomioka, M. Vojnovic
- Computer Science, Mathematics
- NIPS
- 7 October 2016

Parallel implementations of stochastic gradient descent (SGD) have received significant research attention, thanks to its excellent scalability properties. A fundamental barrier when parallelizing… Expand

Norm-Based Capacity Control in Neural Networks

- Behnam Neyshabur, Ryota Tomioka, Nathan Srebro
- Computer Science, Mathematics
- COLT
- 27 February 2015

We investigate the capacity, convexity and characterization of a general family of norm-constrained feed-forward networks.

Estimation of low-rank tensors via convex optimization

- Ryota Tomioka, K. Hayashi, H. Kashima
- Mathematics
- 5 October 2010

In this paper, we propose three approaches for the estimation of the Tucker decomposition of multi-way arrays (tensors) from partial observations. All approaches are formulated as convex minimization… Expand

Tensor factorization using auxiliary information

- Atsuhiro Narita, K. Hayashi, Ryota Tomioka, H. Kashima
- Computer Science
- Data Mining and Knowledge Discovery
- 1 September 2012

Most of the existing analysis methods for tensors (or multi-way arrays) only assume that tensors to be completed are of low rank. However, for example, when they are applied to tensor completion… Expand

Convex Tensor Decomposition via Structured Schatten Norm Regularization

- Ryota Tomioka, T. Suzuki
- Computer Science, Mathematics
- NIPS
- 26 March 2013

We discuss structured Schatten norms for tensor decomposition that includes two recently proposed norms ("overlapped" and "latent") for convex-optimization-based tensor decomposition, and connect… Expand

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

- Behnam Neyshabur, Ryota Tomioka, Nathan Srebro
- Computer Science, Mathematics
- ICLR
- 19 December 2014

We present experiments demonstrating that some other form of capacity control, different from network size, plays a central role in learning multilayer feed-forward networks. We argue, partially… Expand

Statistical Performance of Convex Tensor Decomposition

- Ryota Tomioka, T. Suzuki, K. Hayashi, H. Kashima
- Mathematics, Computer Science
- NIPS
- 12 December 2011

We analyze the statistical performance of a recently proposed convex tensor decomposition algorithm. Conventionally tensor decomposition has been formulated as non-convex optimization problems, which… Expand

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

- Diane Bouchacourt, Ryota Tomioka, Sebastian Nowozin
- Computer Science, Mathematics
- AAAI
- 24 May 2017

We would like to learn a representation of the data which decomposes an observation into factors of variation which we can independently control. Specifically, we want to use minimal supervision to… Expand