New methods using natural gradient for structured optimization.
problem Structured optimization problems.
method Structured second-order methods via natural gradient descent.
result Efficiency demonstrated on non-convex and deep learning problems.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “natural gradient methods”
Natural gradient simplification for deep learning networks.
problem Efficiency in training deep Bayesian networks.
method Analysis of two geometries of Fisher information matrix and development of a method to simplify natural gradient for the second geometry.
result A method to simplify natural gradient for deep networks using an auxiliary recognition model.
New method for natural policy gradients converges linearly.
problem Improving natural policy gradient methods for better convergence.
method Fisher-Rao gradient flow applied to state-action distributions.
result Linear convergence rate with geometry-dependent factor.
Natural Gradients in Practice: Non-Conjugate Variational Inference in Gaussian Process Modelsstat.ML
The natural gradient method has been used effectively in conjugate Gaussian process models, but the non-conjugate case has been largely unexplored. We examine how natural gradients can be used in non-conjugate stochastic settings, together with hyperparameter learning. We conclude that the natural gradient can signific…
A new method uses natural gradients for efficient distribution optimization.
problem Challenges in computing natural gradients for many distributions.
method Reframe optimization as a surrogate distribution with easy natural gradient computation.
result Expands set of distributions efficiently targetable with natural gradients.
Natural-gradient methods enable fast and simple algorithms for variational inference, but due to computational difficulties, their use is mostly limited to \emph{minimal} exponential-family (EF) approximations. In this paper, we extend their application to estimate \emph{structured} approximations such as mixtures of E…
In optimization, the natural gradient method is well-known for likelihood maximization. The method uses the Kullback-Leibler divergence, corresponding infinitesimally to the Fisher-Rao metric, which is pulled back to the parameter space of a family of probability distributions. This way, gradients with respect to the p…
Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learningcs.LG
Paper presents a rank-1 approximation method for natural policy gradients in deep RL.
problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.
Square-root natural-gradient improves variational inference convergence.
problem Challenges in establishing theoretical convergence guarantees for natural-gradient descent.
method Square-root parameterization for Gaussian covariance.
result Establishes novel convergence guarantees for natural-gradient Gaussian inference.
Improved VI method for deep mixed models in finance.
problem Inaccurate and slow variational inference in high dimensions.
method Natural gradient hybrid VI method targeting joint posterior.
result Natural gradient method is faster and more accurate than existing methods.
Solves POMDPs with recurrent neural networks and natural policy gradient.
problem Non-stationarity in optimal policies of POMDPs.
method Integrates recurrent neural networks into natural policy gradient and temporal difference learning.
result Non-asymptotic theoretical guarantees for global optimality up to function approximation.
Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically analyze this method and its properties, and show how it can be viewed as a type of 2…
Researchers propose a non-monotone quantum natural gradient for quantum systems.
problem Applying natural gradient methods to quantum systems without monotonicity.
method Introducing a non-monotone quantum natural gradient (QNG) and demonstrating its superiority over conventional QNG.
result Non-monotone QNG outperforms conventional QNG in terms of convergence speed.
Quantum method speeds up VB estimation in machine learning.
problem Prohibitively expensive natural gradient in high dimensions.
method Regression-based natural gradient estimation with quantum matrix inversion.
result Quantum method enables efficient VB estimation.
Bayesian inference plays an important role in advancing machine learning, but faces computational challenges when applied to complex models such as deep neural networks. Variational inference circumvents these challenges by formulating Bayesian inference as an optimization problem and solving it using gradient-based op…
This work proposes a new method for variational inference using Wasserstein gradient descent.
problem Optimizing variational parameters to match a true posterior distribution.
method Reinterpreting VI as an optimization problem over a variational parameter space, using Wasserstein gradient descent.
result The proposed Wasserstein gradient descent can be seen as a generalization of existing optimization techniques in VI.
Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a st…
Many machine learning problems can be expressed as the optimization of some cost functional over a parametric family of probability distributions. It is often beneficial to solve such optimization problems using natural gradient methods. These methods are invariant to the parametrization of the family, and thus can yie…
Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method, noisy natural gradient, is a surprisingly simple method to fit expressive poste…
Paper proposes ZO-NGD for more efficient black-box attacks.
problem Vulnerability of state-of-the-art DNNs to adversarial attacks.
method Zeroth-order natural gradient descent (ZO-NGD) for black-box attacks.
result ZO-NGD achieves significantly lower model query complexities.
Inversion-free natural gradient method for Riemannian manifolds.
problem Hindered by the need for Euclidean space, Fisher information matrix inversion, and computational cost.
method Intrinsic, inversion-free natural gradient method on Riemannian manifolds, using moving approximation of inverse FIM.
result Almost-sure convergence rates and sub-quadratic storage complexity for large-scale applications.
This technical report constructs a theoretical framework to relate standard Taylor approximation based optimisation methods with Natural Gradient (NG), a method which is Fisher efficient with probabilistic models. Such a framework will be shown to also provide mathematical justification to combine higher order methods …
Improved Bayesian learning rule handles positive-definite constraints efficiently.
problem Bayesian learning rule struggles with positive-definite constraints.
method Proposes an improved rule using Riemannian gradient methods for block-coordinate natural parameterization.
result Outperforms existing methods without increased computation.
Unified perspective on natural gradient methods for GMMs, improving variational inference.
problem Efficiently learning multi-modal approximations of complex distributions.
method Comparison and optimization of VIPS and iBayes-GMM methods for Gaussian mixture models.
result Hybrid approach significantly outperforms both VIPS and iBayes-GMM.
VB uses natural gradients in information geometry.
problem Estimating or computing natural gradients in VB.
method Natural-gradient descent algorithm and Bayesian Learning Rule.
result Simplification of Bayes' rule and generalization of quadratic surrogates.
The paper proposes a method to train time-varying generative models using natural gradients.
problem Training time-varying generative models efficiently and accurately.
method Projecting generative model parameters onto an exponential family manifold and optimizing using natural gradient descent.
result The proposed method efficiently approximates the natural gradient and can be applied to various exponential family models.
NG+ method improves deep learning efficiency and accuracy.
problem Efficiency and accuracy in deep learning models.
method Proposes NG+ method using matrix-product natural gradient approach.
result Established global convergence and provided regret bound.
Derives Mirror Descent from gradient flow on a Riemannian manifold.
problem No specific problem stated; focuses on derivation.
method Derives Mirror Descent from gradient flow on a Riemannian manifold with a natural discretization.
result Generalizes Mirror Descent to non-Hessian metrics.
We present practical Levenberg-Marquardt variants of Gauss-Newton and natural gradient methods for solving non-convex optimization problems that arise in training deep neural networks involving enormous numbers of variables and huge data sets. Our methods use subsampled Gauss-Newton or Fisher information matrices and e…
Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value gradients is desirable as policy improvement occurs along the direction of stee…
We develop a more efficient NGD method for structured parameters.
problem Computational challenges in NGD for structured parameter spaces.
method Local-parameter coordinates to simplify Fisher-matrix computations.
result New structured second-order algorithms and learning methods.
We study the Wasserstein natural gradient in parametric statistical models with continuous sample spaces. Our approach is to pull back the -Wasserstein metric tensor in the probability density space to a parameter space, equipping the latter with a positive definite metric tensor, under which it becomes a Riemanni…
The (stochastic) gradient descent and the multiplicative update method are probably the most popular algorithms in machine learning. We introduce and study a new regularization which provides a unification of the additive and multiplicative updates. This regularization is derived from an hyperbolic analogue of the entr…
Paper improves online time series forecasting by combining natural gradient and robust t-distribution.
problem Online time series forecasting challenges in rapidly adapting to evolving data.
method Reframed neural network optimization as a parameter filtering problem, using natural gradient and Student's t likelihood.
result Natural Score-driven Replay (NatSR) achieves stronger forecasting performance than state-of-the-art methods.
Improves understanding of stochastic NGVI convergence rates.
problem Lack of knowledge about non-asymptotic convergence rates in stochastic NGVI.
method Proved non-asymptotic convergence rates for conjugate likelihoods and showed implicit optimization for non-conjugate likelihoods.
result First non-asymptotic convergence rate for stochastic NGVI in conjugate likelihoods.
BONG optimizes Bayesian inference online with natural gradient descent.
problem Sequential Bayesian inference in online settings.
method Bayesian online natural gradient (BONG) approach based on variational Bayes.
result BONG outperforms other online VB methods in non-conjugate settings.
Stochastic variational inference (SVI) lets us scale up Bayesian computation to massive data. It uses stochastic optimization to fit a variational distribution, following easy-to-compute noisy natural gradients. As with most traditional stochastic optimization methods, SVI takes precautions to use unbiased stochastic g…
AOPU stabilizes NN training by approximating natural gradient, improving stability and convergence.
problem Stability and interpretability in online NN training for industrial soft sensors.
method AOPU truncates gradient backpropagation, optimizing trackable parameters, and approximating natural gradient.
result AOPU achieves stable convergence and superior performance on chemical process datasets.
New algorithm for risk-sensitive reinforcement learning with natural policy gradients.
problem Risk-sensitive reinforcement learning with downside risk constraints.
method Introduce a new Bellman equation to estimate the lower partial moment of returns, use natural policy gradients, and extend Reward Constrained Policy Optimization.
result Sample-efficient estimation of partial moments and effective risk-sensitive control.
We introduce a simple algorithm, True Asymptotic Natural Gradient Optimization (TANGO), that converges to a true natural gradient descent in the limit of small learning rates, without explicit Fisher matrix estimation. For quadratic models the algorithm is also an instance of averaged stochastic gradient, where the par…
A deep neural network is a hierarchical nonlinear model transforming input signals to output signals. Its input-output relation is considered to be stochastic, being described for a given input by a parameterized conditional probability distribution of outputs. The space of parameters consisting of weights and biases i…
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradientcs.LG
Uncertainty estimation in large deep-learning models is a computationally challenging task, where it is difficult to form even a Gaussian approximation to the posterior distribution. In such situations, existing methods usually resort to a diagonal approximation of the covariance matrix despite, the fact that these mat…
This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm belongs to the family of truncated Newton methods and exploits an efficient matrix-vector product to avoid explicitely storing the natural g…
A new algorithm for training generative models using Sinkhorn divergence.
problem Training generative adversarial networks (GANs).
method Sinkhorn Natural Gradient (SiNG) algorithm for steepest descent on probability space.
result Explicit expression and efficient evaluation of the Sinkhorn information matrix (SIM).
NVA combines variational posteriors, annealing, and natural-gradient learning for multimodal optimization.
problem Finding multiple global and local modes in nonconvex objectives.
method NVA integrates variational posteriors, annealing, and natural-gradient learning.
result NVA outperforms gradient descent and evolution strategies on simulations and real-world problems.
The natural gradient allows for more efficient gradient descent by removing dependencies and biases inherent in a function's parameterization. Several papers present the topic thoroughly and precisely. It remains a very difficult idea to get your head around however. The intent of this note is to provide simple intuiti…
Variational inference transforms posterior inference into parametric optimization thereby enabling the use of latent variable models where otherwise impractical. However, variational inference can be finicky when different variational parameters control variables that are strongly correlated under the model. Traditiona…
Natural gradient descent avoids the magic of model parametrization, leading to different optimization outcomes.
problem Understanding the impact of model parametrization on optimization and generalization in deep learning.
method Characterization of natural gradient flow in deep linear networks and nonlinear neural networks.
result Natural gradient descent fails to generalize in some cases, while gradient descent with the right architecture performs well.