Tracking Performance of Online Stochastic Learners
- URL: http://arxiv.org/abs/2004.01942v1
- Date: Sat, 4 Apr 2020 14:16:27 GMT
- Title: Tracking Performance of Online Stochastic Learners
- Authors: Stefan Vlaski, Elsa Rizk, Ali H. Sayed
- Abstract summary: Online algorithms are popular in large-scale learning settings due to their ability to compute updates on the fly, without the need to store and process data in large batches.
When a constant step-size is used, these algorithms also have the ability to adapt to drifts in problem parameters, such as data or model properties, and track the optimal solution with reasonable accuracy.
We establish a link between steady-state performance derived under stationarity assumptions and the tracking performance of online learners under random walk models.
- Score: 57.14673504239551
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The utilization of online stochastic algorithms is popular in large-scale
learning settings due to their ability to compute updates on the fly, without
the need to store and process data in large batches. When a constant step-size
is used, these algorithms also have the ability to adapt to drifts in problem
parameters, such as data or model properties, and track the optimal solution
with reasonable accuracy. Building on analogies with the study of adaptive
filters, we establish a link between steady-state performance derived under
stationarity assumptions and the tracking performance of online learners under
random walk models. The link allows us to infer the tracking performance from
steady-state expressions directly and almost by inspection.
Related papers
- Towards An Online Incremental Approach to Predict Students Performance [0.8287206589886879]
We propose a memory-based online incremental learning approach for updating an online classifier.
Our approach achieves a notable improvement in model accuracy, with an enhancement of nearly 10% compared to the current state-of-the-art.
arXiv Detail & Related papers (2024-05-03T17:13:26Z) - Online Test-Time Adaptation of Spatial-Temporal Traffic Flow Forecasting [13.770733370640565]
This paper conducts the first study of the online test-time adaptation techniques for spatial-temporal traffic flow forecasting problems.
We propose an Adaptive Double Correction by Series Decomposition (ADCSD) method, which first decomposes the output of the trained model into seasonal and trend-cyclical parts.
In the proposed ADCSD method, instead of fine-tuning the whole trained model during the testing phase, a lite network is attached after the trained model, and only the lite network is fine-tuned in the testing process each time a data entry is observed.
arXiv Detail & Related papers (2024-01-08T12:04:39Z) - DTC: Deep Tracking Control [16.2850135844455]
We propose a hybrid control architecture that combines the advantages of both worlds to achieve greater robustness, foot-placement accuracy, and terrain generalization.
A deep neural network policy is trained in simulation, aiming to track the optimized footholds.
We demonstrate superior robustness in the presence of slippery or deformable ground when compared to model-based counterparts.
arXiv Detail & Related papers (2023-09-27T07:57:37Z) - Value function estimation using conditional diffusion models for control [62.27184818047923]
We propose a simple algorithm called Diffused Value Function (DVF)
It learns a joint multi-step model of the environment-robot interaction dynamics using a diffusion model.
We show how DVF can be used to efficiently capture the state visitation measure for multiple controllers.
arXiv Detail & Related papers (2023-06-09T18:40:55Z) - Low-rank extended Kalman filtering for online learning of neural
networks from streaming data [71.97861600347959]
We propose an efficient online approximate Bayesian inference algorithm for estimating the parameters of a nonlinear function from a potentially non-stationary data stream.
The method is based on the extended Kalman filter (EKF), but uses a novel low-rank plus diagonal decomposition of the posterior matrix.
In contrast to methods based on variational inference, our method is fully deterministic, and does not require step-size tuning.
arXiv Detail & Related papers (2023-05-31T03:48:49Z) - A Log-Linear Non-Parametric Online Changepoint Detection Algorithm based
on Functional Pruning [5.202524136984542]
We build a flexible nonparametric approach to detect a change in the distribution of a sequence.
Thanks to functional pruning ideas, NP-FOCuS has a computational cost that is log-linear in the number of observations.
In terms of detection power, NP-FOCuS is seen to outperform current nonparametric online changepoint techniques in a variety of settings.
arXiv Detail & Related papers (2023-02-06T11:50:02Z) - An Adaptive Framework for Learning Unsupervised Depth Completion [59.17364202590475]
We present a method to infer a dense depth map from a color image and associated sparse depth measurements.
We show that regularization and co-visibility are related via the fitness of the model to data and can be unified into a single framework.
arXiv Detail & Related papers (2021-06-06T02:27:55Z) - Self-Tuning Stochastic Optimization with Curvature-Aware Gradient
Filtering [53.523517926927894]
We explore the use of exact per-sample Hessian-vector products and gradients to construct self-tuning quadratics.
We prove that our model-based procedure converges in noisy gradient setting.
This is an interesting step for constructing self-tuning quadratics.
arXiv Detail & Related papers (2020-11-09T22:07:30Z) - Meta Learning MPC using Finite-Dimensional Gaussian Process
Approximations [0.9539495585692008]
Two key factors that hinder the practical applicability of learning methods in control are their high computational complexity and limited generalization capabilities to unseen conditions.
This paper makes use of a meta-learning approach for adaptive model predictive control, by learning a system model that leverages data from previous related tasks.
arXiv Detail & Related papers (2020-08-13T15:59:38Z) - How Training Data Impacts Performance in Learning-based Control [67.7875109298865]
This paper derives an analytical relationship between the density of the training data and the control performance.
We formulate a quality measure for the data set, which we refer to as $rho$-gap.
We show how the $rho$-gap can be applied to a feedback linearizing control law.
arXiv Detail & Related papers (2020-05-25T12:13:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.