English
Related papers

Related papers: Eigenvalue Corrected Noisy Natural Gradient

200 papers

Gaussian multiplicative noise is commonly used as a stochastic regularisation technique in training of deterministic neural networks. A recent paper reinterpreted the technique as a specific algorithm for approximate inference in Bayesian…

Machine Learning · Statistics 2017-11-09 Jiri Hron , Alexander G. de G. Matthews , Zoubin Ghahramani

Correlation between microstructure noise and latent financial logarithmic returns is an empirically relevant phenomenon with sound theoretical justification. With few notable exceptions, all integrated variance estimators proposed in the…

Computation · Statistics 2019-05-29 Stefano Peluso , Antonietta Mira , Pietro Muliere

Using quasi-Newton methods in stochastic optimization is not a trivial task given the difficulty of extracting curvature information from the noisy gradients. Moreover, pre-conditioning noisy gradient observations tend to amplify the noise.…

Optimization and Control · Mathematics 2024-04-02 Andre Carlon , Luis Espath , Raul Tempone

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…

Machine Learning · Computer Science 2019-01-15 Aaron Mishkin , Frederik Kunstner , Didrik Nielsen , Mark Schmidt , Mohammad Emtiyaz Khan

In this work, we study the problem of learning the volatility under market microstructure noise. Specifically, we consider noisy discrete time observations from a stochastic differential equation and develop a novel computational method to…

Methodology · Statistics 2024-03-19 Shota Gugushvili , Frank van der Meulen , Moritz Schauer , Peter Spreij

We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017). We show that each variant of data noising is an instance of Bayesian recurrent neural networks with a particular…

Computation and Language · Computer Science 2019-01-29 Lingpeng Kong , Gabor Melis , Wang Ling , Lei Yu , Dani Yogatama

Bayesian inference for high-dimensional inverse problems is computationally costly and requires selecting a suitable prior distribution. Amortized variational inference addresses these challenges via a neural network that approximates the…

Machine Learning · Statistics 2023-01-19 Ali Siahkoohi , Gabrio Rizzuti , Rafael Orozco , Felix J. Herrmann

Second-order methods such as KFAC can be useful for neural net training. However, they are often memory-inefficient since their preconditioning Kronecker factors are dense, and numerically unstable in low precision as they require matrix…

Machine Learning · Computer Science 2024-07-24 Wu Lin , Felix Dangel , Runa Eschenhagen , Kirill Neklyudov , Agustinus Kristiadi , Richard E. Turner , Alireza Makhzani

Bayesian neural networks with latent variables are scalable and flexible probabilistic models: They account for uncertainty in the estimation of the network weights and, by making use of latent variables, can capture complex noise patterns…

Machine Learning · Statistics 2018-06-19 Stefan Depeweg , José Miguel Hernández-Lobato , Finale Doshi-Velez , Steffen Udluft

Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the…

Machine Learning · Computer Science 2021-02-08 Minyoung Kim , Vladimir Pavlovic

Noise characterization in MRI has multiple applications, including quality assurance and protocol optimization. It is particularly important in the presence of parallel imaging acceleration, where the noise distribution can contain severe…

Despite its long history, Bayesian neural networks (BNNs) and variational training remain underused in practice: standard Gaussian posteriors misalign with network geometry, KL terms can be brittle in high dimensions, and implementations…

Machine Learning · Computer Science 2025-09-09 Carlos Stein Brito

We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in data. While many recent attempts at factor disentanglement have focused on sophisticated learning…

Machine Learning · Computer Science 2019-09-10 Minyoung Kim , Yuting Wang , Pritish Sahu , Vladimir Pavlovic

Reliable state estimation depends on accurately modeled noise covariances, which are difficult to determine in practice. This paper formulates the noise covariance estimation as a bilevel optimization problem that factorizes the joint…

Systems and Control · Electrical Eng. & Systems 2025-12-08 Haoying Li , Yifan Peng , Yuchi Wu , Junfeng Wu

In this paper, we propose a novel high-dimensional time-varying coefficient estimator for noisy high-frequency observations with a factor structure. In high-frequency finance, we often observe that noises dominate the signal of underlying…

Methodology · Statistics 2026-05-12 Minseok Shin , Donggyu Kim

Several studies have shown the ability of natural gradient descent to minimize the objective function more efficiently than ordinary gradient descent based methods. However, the bottleneck of this approach for training deep neural networks…

Neural and Evolutionary Computing · Computer Science 2022-10-17 Abdoulaye Koroko , Ani Anciaux-Sedrakian , Ibtihel Ben Gharbia , Valérie Garès , Mounir Haddou , Quang Huy Tran

Adding noises to artificial neural network(ANN) has been shown to be able to improve robustness in previous work. In this work, we propose a new technique to compute the pathwise stochastic gradient estimate with respect to the standard…

Machine Learning · Computer Science 2021-02-10 Li Xiao , Zeliang Zhang , Yijie Peng

Forward gradient learning computes a noisy directional gradient and is a biologically plausible alternative to backprop for learning deep neural networks. However, the standard forward gradient algorithm, when applied naively, suffers from…

Machine Learning · Computer Science 2023-03-03 Mengye Ren , Simon Kornblith , Renjie Liao , Geoffrey Hinton

Variational quantum algorithms are promising tools whose efficacy depends on their optimisation method. For noise-free unitary circuits, the quantum generalisation of natural gradient descent has been introduced and shown to be equivalent…

Quantum Physics · Physics 2023-09-12 Bálint Koczor , Simon C. Benjamin

We introduce a new method for learning Bayesian neural networks, treating them as a stack of multivariate Bayesian linear regression models. The main idea is to infer the layerwise posterior exactly if we know the target outputs of each…

Machine Learning · Computer Science 2024-11-20 Richard Kurle , Alexej Klushyn , Ralf Herbrich