BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

R. Bhushan Gopaluni

R. Bhushan Gopaluni appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
ComputationMachine LearningApplicationseess.SYMethodologySystems and Controlmath.OC

Catalog footprint

What is connected

8works
7topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

8 published item(s)

preprint2026arXiv

Error whitening: Why Gauss-Newton outperforms Newton

The Gauss-Newton matrix is widely viewed as a positive semidefinite approximation of the Hessian, yet mounting empirical evidence shows that Gauss-Newton descent outperforms Newton's method. We adopt a function space perspective to analyze this phenomenon. We show that the generalized Gauss-Newton (GGN) matrix projects the Newton direction in function space onto the model's tangent space, while a Jacobian-only variant obtained by applying the least squares Gauss-Newton matrix to non-least squares losses projects the function space loss gradient onto this same tangent space. Both projections eliminate distortions from the model's parameterization. Specifically, the evolution of the prediction-target mismatch depends on the model's parameterization through the matrix $JJ^\top$ where $J$ is the Jacobian of the model with respect to its parameters. The projections effectively replace $JJ^\top$ with the identity. We call this effect error whitening. Once the parameterization is removed, the prediction-target mismatch evolves according to dynamics dictated by the structure of the loss and the projection produced by the optimizer. Error whitening is a special property of Gauss-Newton descent that rigorously distinguishes it from Newton's method. We empirically demonstrate that Gauss-Newton optimizers follow the theoretically predicted function space dynamics and outperforms Newton's method, Adam, and Muon across case studies spanning supervised learning, physics-informed deep learning, and approximate dynamic programming.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system

The carbon-capturing process with the aid of CO2 removal technology (CDRT) has been recognised as an alternative and a prominent approach to deep decarbonisation. However, the main hindrance is the enormous energy demand and the economic implication of CDRT if not effectively managed. Hence, a novel deep reinforcement learning agent (DRL), integrated with an automated hyperparameter selection feature, is proposed in this study for the real-time scheduling of a multi-energy system coupled with CDRT. Post-carbon capture systems (PCCS) and direct-air capture systems (DACS) are considered CDRT. Various possible configurations are evaluated using real-time multi-energy data of a district in Arizona and CDRT parameters from manufacturers' catalogues and pilot project documentation. The simulation results validate that an optimised soft-actor critic (SAC) algorithm outperformed the TD3 algorithm due to its maximum entropy feature. We then trained four (4) SAC agents, equivalent to the number of considered case studies, using optimised hyperparameter values and deployed them in real time for evaluation. The results show that the proposed DRL agent can meet the prosumers' multi-energy demand and schedule the CDRT energy demand economically without specified constraints violation. Also, the proposed DRL agent outperformed rule-based scheduling by 23.65%. However, the configuration with PCCS and solid-sorbent DACS is considered the most suitable configuration with a high CO2 captured-released ratio of 38.54, low CO2 released indicator value of 2.53, and a 36.5% reduction in CDR cost due to waste heat utilisation and high absorption capacity of the selected sorbent. However, the adoption of CDRT is not economically viable at the current carbon price. Finally, we showed that CDRT would be attractive at a carbon price of 400-450USD/ton with the provision of tax incentives by the policymakers.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning

Deep reinforcement learning (RL) is an optimization-driven framework for producing control strategies for general dynamical systems without explicit reliance on process models. Good results have been reported in simulation. Here we demonstrate the challenges in implementing a state of the art deep RL algorithm on a real physical system. Aspects include the interplay between software and existing hardware; experiment design and sample efficiency; training subject to input constraints; and interpretability of the algorithm and control law. At the core of our approach is the use of a PID controller as the trainable RL policy. In addition to its simplicity, this approach has several appealing features: No additional hardware needs to be added to the control system, since a PID controller can easily be implemented through a standard programmable logic controller; the control law can easily be initialized in a "safe'' region of the parameter space; and the final product -- a well-tuned PID controller -- has a form that practitioners can reason about and deploy with confidence.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Deep Reinforcement Learning for Process Control: A Primer for Beginners

Advanced model-based controllers are well established in process industries. However, such controllers require regular maintenance to maintain acceptable performance. It is a common practice to monitor controller performance continuously and to initiate a remedial model re-identification procedure in the event of performance degradation. Such procedures are typically complicated and resource-intensive, and they often cause costly interruptions to normal operations. In this paper, we exploit recent developments in reinforcement learning and deep learning to develop a novel adaptive, model-free controller for general discrete-time processes. The DRL controller we propose is a data-based controller that learns the control policy in real time by merely interacting with the process. The effectiveness and benefits of the DRL controller are demonstrated through many simulations.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

A particle filter approach to approximate posterior Cramér-Rao lower bound

The posterior Cramér-Rao lower bound (PCRLB) derived in Tichavský et al., 1998, provides a bound on the mean square error (MSE) obtained with any non-linear state filter. Computing the PCRLB involves solving complex, multi-dimensional expectations, which do not lend themselves to an easy analytical solution. Furthermore, any attempt to approximate it using numerical or simulation based approaches require a priori access to the true states, which may not be available, except in simulations or in carefully designed experiments. To allow recursive approximation of the PCRLB when the states are hidden or unmeasured, a new approach based on sequential Monte-Carlo (SMC) or particle filters (PF) is proposed. The approach uses SMC methods to estimate the hidden states using a sequence of the available sensor measurements. The developed method is general and can be used to approximate the PCRLB in non-linear systems with non-Gaussian state and sensor noise. The efficacy of the developed method is illustrated on two simulation examples, including a practical problem of ballistic target tracking at re-entry phase.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Error analysis in Bayesian identification of non-linear state-space models

In the last two decades, several methods based on sequential Monte Carlo (SMC) and Markov chain Monte Carlo (MCMC) have been proposed for Bayesian identification of stochastic non-linear state-space models (SSMs). It is well known that the performance of these simulation based identification methods depends on the numerical approximations used in their design. We propose the use of posterior Cramér-Rao lower bound (PCRLB) as a mean square error (MSE) bound. Using PCRLB, a systematic procedure is developed to analyse the estimates delivered by Bayesian identification methods in terms of bias, MSE, and efficiency. The efficacy and utility of the proposed approach is illustrated through a numerical example.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Input design for Bayesian identification of non-linear state-space models

We propose an algorithm for designing optimal inputs for on-line Bayesian identification of stochastic non-linear state-space models. The proposed method relies on minimization of the posterior Cramér Rao lower bound derived for the model parameters, with respect to the input sequence. To render the optimization problem computationally tractable, the inputs are parametrized as a multi-dimensional Markov chain in the input space. The proposed approach is illustrated through a simulation example.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

On-line Bayesian parameter estimation in general non-linear state-space models: A tutorial and new results

On-line estimation plays an important role in process control and monitoring. Obtaining a theoretical solution to the simultaneous state-parameter estimation problem for non-linear stochastic systems involves solving complex multi-dimensional integrals that are not amenable to analytical solution. While basic sequential Monte-Carlo (SMC) or particle filtering (PF) algorithms for simultaneous estimation exist, it is well recognized that there is a need for making these on-line algorithms non-degenerate, fast and applicable to processes with missing measurements. To overcome the deficiencies in traditional algorithms, this work proposes a Bayesian approach to on-line state and parameter estimation. Its extension to handle missing data in real-time is also provided. The simultaneous estimation is performed by filtering an extended vector of states and parameters using an adaptive sequential-importance-resampling (SIR) filter with a kernel density estimation method. The approach uses an on-line optimization algorithm based on Kullback-Leibler (KL) divergence to allow adaptation of the SIR filter for combined state-parameter estimation. An optimal tuning rule to control the width of the kernel and the variance of the artificial noise added to the parameters is also proposed. The approach is illustrated through numerical examples.

0 citations0 reviewsNo code linkedOpen access