Ryo Karakida

Ryo Karakida

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2021 in Neural Computation
Verified
Journal Article
Open access
PDF file
RKRyo Karakida
Ryo Karakida
SAShotaro Akaho
Shotaro Akaho
SAShun-Ichi Amari
Shun-Ichi Amari
The Fisher information matrix (FIM) plays an essential role in statistics and machine learning as a Riemannian metric tensor or a component of the Hessian matrix of loss functions. Focusing on the FIM and its variants in deep neural networks (DNNs), we reveal their characteristic scale dependence on the network width, depth, and sample size when the network has random weights and is sufficiently wide. This study covers two widely used FIMs for regression with linear output and for classification with softmax output. Both FIMs asymptotically show pathological eigenvalue spectra in the sense that a small number of eigenvalues become large outliers depending on the width or sample size, while the others are much smaller. It implies that the local shape of the parameter space or loss landscape is very sharp in a few specific directions while almost flat in the other directions. In particular, the softmax output disperses the outliers and makes a tail of the eigenvalue density spread from the bulk. We also show that pathological spectra appear in other variants of FIMs: one is the neural tangent kernel; another is a metric for the input signal and feature space that arises from feedforward signal propagation. Thus, we provide a unified perspective on the FIM and its variants that will lead to more quantitative understanding of learning in large-scale DNNs.

1 January 2018 in Neural Computation
Verified
Journal Article
Closed access
SAShun-Ichi Amari
Shun-Ichi Amari
TOTomoko Ozeki
Tomoko Ozeki
RKRyo Karakida
Ryo Karakida
YYYuki Yoshida
Yuki Yoshida
MOMasato Okada
Masato Okada
The dynamics of supervised learning play a main role in deep learning, which takes place in the parameter space of a multilayer perceptron (MLP). We review the history of supervised stochastic gradient learning, focusing on its singular structure and natural gradient. The parameter space includes singular regions in which parameters are not identifiable. One of our results is a full exploration of the dynamical behaviors of stochastic gradient learning in an elementary singular network. The bad news is its pathological nature, in which part of the singular region becomes an attractor and another part a repulser at the same time, forming a Milnor attractor. A learning trajectory is attracted by the attractor region, staying in it for a long time, before it escapes the singular region through the repulser region. This is typical of plateau phenomena in learning. We demonstrate the strange topology of a singular region by introducing blow-down coordinates, which are useful for analyzing the natural gradient dynamics. We confirm that the natural gradient dynamics are free of critical slowdown. The second main result is the good news: the interactions of elementary singular networks eliminate the attractor part and the Milnor-type attractors disappear. This explains why large-scale networks do not suffer from serious critical slowdowns due to singularities. We finally show that the unit-wise natural gradient is effective for learning in spite of its low computational cost.

1 May 2019 in Neural Computation
Verified
Journal Article
Closed access
SAShun-Ichi Amari
Shun-Ichi Amari
RKRyo Karakida
Ryo Karakida
MOMasafumi Oizumi
Masafumi Oizumi
MCMarco Cuturi
Marco Cuturi
We propose a new divergence on the manifold of probability distributions, building on the entropic regularization of optimal transportation problems. As Cuturi ( 2013 ) showed, regularizing the optimal transport problem with an entropic term is known to bring several computational benefits. However, because of that regularization, the resulting approximation of the optimal transport cost does not define a proper distance or divergence between probability distributions. We recently tried to introduce a family of divergences connecting the Wasserstein distance and the Kullback-Leibler divergence from an information geometry point of view (see Amari, Karakida, & Oizumi, 2018 ). However, that proposal was not able to retain key intuitive aspects of the Wasserstein geometry, such as translation invariance, which plays a key role when used in the more general problem of computing optimal transport barycenters. The divergence we propose in this work is able to retain such properties and admits an intuitive interpretation.

1 December 2021 in Journal of Statistical Mechanics: Theory and Experiment
Verified
Journal Article
Closed access
RKRyo Karakida
Ryo Karakida
KOKazuki Osawa
Kazuki Osawa
Natural gradient descent (NGD) helps to accelerate the convergence of gradient descent dynamics, but it requires approximations in large-scale deep neural networks because of its high computational cost. Empirical studies have confirmed that some NGD methods with approximate Fisher information converge sufficiently fast in practice. Nevertheless, it remains unclear from the theoretical perspective why and under what conditions such heuristic approximations work well. In this work, we reveal that, under specific conditions, NGD with approximate Fisher information achieves the same fast convergence to global minima as exact NGD. We consider deep neural networks in the infinite-width limit, and analyze the asymptotic training dynamics of NGD in function space via the neural tangent kernel. In the function space, the training dynamics with the approximate Fisher information are identical to those with the exact Fisher information, and they converge quickly. The fast convergence holds in layer-wise approximations; for instance, in block diagonal approximation where each block corresponds to a layer as well as in block tri-diagonal and K-FAC approximations. We also find that a unit-wise approximation achieves the same fast convergence under some assumptions. All of these different approximations have an isotropic gradient in the function space, and this plays a fundamental role in achieving the same convergence properties in training. Thus, the current study gives a novel and unified theoretical foundation with which to understand NGD methods in deep learning.

12 July 2023 in Neural Computation
Verified
Journal Article
Closed access
PDF file
TOToshihiro Ota
Toshihiro Ota
RKRyo Karakida
Ryo Karakida
Hopfield networks and Boltzmann machines (BMs) are fundamental energy-based neural network models. Recent studies on modern Hopfield networks have broadened the class of energy functions and led to a unified perspective on general Hopfield networks, including an attention module. In this letter, we consider the BM counterparts of modern Hopfield networks using the associated energy functions and study their salient properties from a trainability perspective. In particular, the energy function corresponding to the attention module naturally introduces a novel BM, which we refer to as the attentional BM (AttnBM). We verify that AttnBM has a tractable likelihood function and gradient for certain special cases and is easy to train. Moreover, we reveal the hidden connections between AttnBM and some single-layer models, namely the gaussian–Bernoulli restricted BM and the denoising autoencoder with softmax units coming from denoising score matching. We also investigate BMs introduced by other energy functions and show that the energy function of dense associative memory models gives BMs belonging to exponential family harmoniums.

1 January 2019 in Nonlinear Theory and Its Applications, IEICE
Verified
Journal Article
Open access
PDF file
SAShun-Ichi Amari
Shun-Ichi Amari
RKRyo Karakida
Ryo Karakida
MOMasafumi Oizumi
Masafumi Oizumi
Deep neural networks are highly nonlinear hierarchical systems. Statistical neurodynamics studies macroscopic behaviors of randomly connected neural networks. We consider a deep feedforward network where input signals are processed layer by layer. The manifold of input signals is embedded in a higher dimensional manifold of the next layer as a curved submanifold, provided the number of neurons is larger than that of inputs. We show geometrical features of the embedded manifold, proving that the manifold enlarges or shrinks locally isotropically so that it is always embedded conformally. We study the curvature of the embedded manifold. The scalar curvature converges to a constant or diverges to infinity slowly. The distance between two signals also changes, converging eventually to a stable fixed value, provided both the number of neurons in a layer and the number of layers tend to infinity. This causes a problem: When we consider a curve in the input space, it is mapped as a continuous curve of fractal nature, but our theory contradictorily suggests that the curve eventually converges to a discrete set of equally spaced points. In reality, the numbers of neurons and layers are finite and thus, it is expected that the finite size effect causes the discrepancies between our theory and reality. Further studies are necessary to understand their implications on information processing.