185 citations · 945 across the 83 of their papers we have counts for
13 papers · 1 filter
Domain Adaptation Regularization for Spectral Pruning
Laurent Dillard, Yosuke Shinya, Taiji Suzuki
Deep Neural Networks (DNNs) have recently been achieving state-of-the-art performance on a variety of computer vision related tasks. However, their computational cost limits their…
Exponential Convergence Rates of Classification Errors on Learning with SGD and Random Features
Shingo Yashima, Atsushi Nitanda, Taiji Suzuki
Although kernel methods are widely used in many learning problems, they have poor scalability to large datasets. To address this problem, sketching and stochastic gradient methods…
Decomposable-Net: Scalable Low-Rank Compression for Neural Networks
Atsushi Yaguchi, Taiji Suzuki, Shuhei Nitta +2
Compressing DNNs is important for the real-world applications operating on resource-constrained devices. However, we typically observe drastic performance deterioration when changi…
Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space
Taiji Suzuki, Atsushi Nitanda
Deep learning has exhibited superior performance for various tasks, especially for high-dimensional datasets, such as images. To understand this property, we investigate the approx…
Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
Yosuke Shinya, Edgar Simo-Serra, Taiji Suzuki
ImageNet pre-training has been regarded as essential for training accurate object detectors for a long time. Recently, it has been shown that object detectors trained from randomly…
Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network
Taiji Suzuki, Hiroshi Abe, Tomoaki Nishimura
One of the biggest issues in deep learning theory is the generalization ability of networks with huge model size. The classical learning theory suggests that overparameterized mode…