English
Related papers

Related papers: Interpretable Gradient Descent for Kalman Gain

200 papers

We consider Kalman filtering problems when the observations are intermittently erased or lost. It was known that the estimates are mean-square unstable when the erasure probability is larger than a certain critical value, and stable…

Optimization and Control · Mathematics 2013-08-29 Se Yong Park , Anant Sahai

The Kalman filter computes the optimal variable-gain using prior knowledge of the initial state and random (process and measurement) noise distributions, which are assumed to be Gaussian with known variance. However, when these…

Systems and Control · Electrical Eng. & Systems 2022-01-31 Hugh Lachlan Kennedy

Multi-channel sparse blind deconvolution, or convolutional sparse coding, refers to the problem of learning an unknown filter by observing its circulant convolutions with multiple input signals that are sparse. This problem finds numerous…

Machine Learning · Statistics 2021-04-07 Laixi Shi , Yuejie Chi

We introduce the inverse Kalman filter, which enables exact matrix-vector multiplication between a covariance matrix from a dynamic linear model and any real-valued vector with linear computational cost. We integrate the inverse Kalman…

Methodology · Statistics 2026-01-27 Xinyi Fang , Mengyang Gu

Optimal decision-making under partial observability requires reasoning about the uncertainty of the environment's hidden state. However, most reinforcement learning architectures handle partial observability with sequence models that have…

Machine Learning · Computer Science 2025-02-20 Carlos E. Luis , Alessandro G. Bottero , Julia Vinogradska , Felix Berkenkamp , Jan Peters

The optimal predictor for a linear dynamical system (with hidden state and Gaussian noise) takes the form of an autoregressive linear filter, namely the Kalman filter. However, a fundamental problem in reinforcement learning and control…

Machine Learning · Computer Science 2019-05-27 Holden Lee , Cyril Zhang

This paper presents a practical and scalable grid-based state estimation method for high-dimensional models with invertible linear dynamics and with highly non-linear measurements, such as the nearly constant velocity model with…

Signal Processing · Electrical Eng. & Systems 2026-01-13 J. Matoušek , J. Krejčí , J. Duník , R. Zanetti

We consider the problem of optimal control for partially observed dynamical systems. Despite its prevalence in practical applications, there are still very few algorithms available, which take uncertainties in the current state estimates…

Optimization and Control · Mathematics 2025-03-18 Sebastian Reich

We introduce $\mathbf{G}$radient Descent with $\mathbf{A}$daptive $\mathbf{M}$omentum $\mathbf{S}$caling ($\mathbf{Grams}$), a novel optimization algorithm that decouples the direction and magnitude of parameter updates in deep learning.…

Machine Learning · Computer Science 2025-03-06 Yang Cao , Xiaoyu Li , Zhao Song

Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work suggests that acceleration often arises near the edge of…

Machine Learning · Computer Science 2026-03-02 Sacchit Kale , Piyushi Manupriya , Pierre Marion , Francis Bach , Anant Raj

Extrapolation is a well-known technique for solving convex optimization and variational inequalities and recently attracts some attention for non-convex optimization. Several recent works have empirically shown its success in some machine…

Optimization and Control · Mathematics 2019-02-06 Yi Xu , Zhuoning Yuan , Sen Yang , Rong Jin , Tianbao Yang

The feedback particle filter (FPF) is an innovative, control-oriented and resampling-free adaptation of the traditional particle filter (PF). In the FPF, individual particles are regulated via a feedback gain, and the corresponding gain…

Optimization and Control · Mathematics 2026-04-08 Ruoyu Wang , Huimin Miao , Xue Luo

We propose a novel adaptive importance sampling algorithm which incorporates Stein variational gradient decent algorithm (SVGD) with importance sampling (IS). Our algorithm leverages the nonparametric transforms in SVGD to iteratively…

Machine Learning · Statistics 2017-07-26 Jun Han , Qiang Liu

A recently developed data-driven Kalman filter requires offline measurement of the process disturbance; a requirement that is often unmet for many practical applications. We propose a solution that parametrizes the Kalman filter exclusively…

Systems and Control · Electrical Eng. & Systems 2025-11-12 Mohamed Abdalmoaty , Roy S. Smith

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner. InfoGAN is a generative adversarial network that…

Machine Learning · Computer Science 2016-06-14 Xi Chen , Yan Duan , Rein Houthooft , John Schulman , Ilya Sutskever , Pieter Abbeel

This paper shows that the implicit bias of gradient descent on linearly separable data is exactly characterized by the optimal solution of a dual optimization problem given by a smoothed margin, even for general losses. This is in contrast…

Machine Learning · Computer Science 2020-11-13 Ziwei Ji , Matus Telgarsky

We conducted a reproducibility study on Integrated Gradients (IG) based methods and the Important Direction Gradient Integration (IDGI) framework. IDGI eliminates the explanation noise in each step of the computation of IG-based methods…

Numerical Analysis · Mathematics 2024-09-17 Shree Singhi , Anupriya Kumari

The error exponent in lossy source coding characterizes the asymptotic decay rate of error probability with respect to blocklength. The Marton's error exponent provides the theoretically optimal bound on this rate. However, computation…

Information Theory · Computer Science 2025-07-29 Jiachuan Ye , Shitong Wu , Lingyi Chen , Wenyi Zhang , Huihui Wu , Hao Wu

We show that running gradient descent with variable learning rate guarantees loss $f(x) \leq 1.1 \cdot f(x^*) + \epsilon$ for the logistic regression objective, where the error $\epsilon$ decays exponentially with the number of iterations…

Machine Learning · Computer Science 2023-06-27 Kyriakos Axiotis , Maxim Sviridenko

This work presents a notion of strong detectability for linear time varying systems affected by unknown inputs. It is shown that this notion is equivalent to detectability of an auxiliary system without unknown inputs. This allows a…

Systems and Control · Electrical Eng. & Systems 2021-03-24 Markus Tranninger , Richard Seeber , Juan G. Rueda-Escobedo , Martin Horn
‹ Prev 1 3 4 5 6 7 10 Next ›