Ritabrata Dutta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Ritabrata Dutta has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
Antonietta Mira
Università della Svizzera Italiana Switzerland
6 shared publicationsLorenzo Pacchiardi
Leverhulme Centre for the Future of Intelligence, University of Cambridge, UK
5 shared publications- Andreas Futschik
Institute of Applied Statistics, Johannes Kepler University Linz, 4040 Linz, Austria
3 shared publications Bastien Chopard
University of Geneva Switzerland
3 shared publications- Yuehao Xu
Department of Experiment & Research, South China Hospital, Medical School Shenzhen University Shenzhen China
3 shared publications Alain Van Meerhaeghe
Affiliation Pneumology Department, ISPPC CHU de Charleroi, Charleroi, Belgium
2 shared publications
Latest Publications
- Open Access
- 10 September 2026
- Published by Springer Nature in Japanese Journal of Statistics and Data Science
- p. 1-51
Prequential posteriors
Data assimilation is a fundamental task in updating forecasting models upon observing new data, with applications ranging from weather prediction to online reinforcement learning. Deep generative forecasting models (DGFMs) have shown excellent performance in these areas, but assimilating data into such models is challenging due to their intractable likelihood functions. This limitation restricts the use of standard Bayesian data assimilation methodologies for DGFMs. To overcome this, we introduce prequential posteriors , based upon a predictive-sequential (prequential) loss function; an approach naturally suited for temporally dependent data which is the focus of forecasting tasks. Since the true data-generating process often lies outside the assumed model class, we adopt an alternative notion of consistency and prove that, under mild conditions, both the prequential loss minimizer and the prequential posterior concentrate around parameters with optimal predictive performance. For scalable inference, we employ easily parallelizable wastefree sequential Monte Carlo (SMC) samplers with preconditioned gradient-based kernels, enabling efficient exploration of high-dimensional parameter spaces such as those in DGFMs. We validate our method on both a synthetic multi-dimensional time series and a real-world meteorological dataset; highlighting its practical utility for data assimilation for complex dynamical systems.
- 10 September 2026
- Published by Springer Nature in Japanese Journal of Statistics and Data Science
- p. 1-51
Open AccessPrequential posteriors
Data assimilation is a fundamental task in updating forecasting models upon observing new data, with applications ranging from weather prediction to online reinforcement learning. Deep generative forecasting models (DGFMs) have shown excellent performance in these areas, but assimilating data into such models is challenging due to their intractable likelihood functions. This limitation restricts the use of standard Bayesian data assimilation methodologies for DGFMs. To overcome this, we introduce prequential posteriors , based upon a predictive-sequential (prequential) loss function; an approach naturally suited for temporally dependent data which is the focus of forecasting tasks. Since the true data-generating process often lies outside the assumed model class, we adopt an alternative notion of consistency and prove that, under mild conditions, both the prequential loss minimizer and the prequential posterior concentrate around parameters with optimal predictive performance. For scalable inference, we employ easily parallelizable wastefree sequential Monte Carlo (SMC) samplers with preconditioned gradient-based kernels, enabling efficient exploration of high-dimensional parameter spaces such as those in DGFMs. We validate our method on both a synthetic multi-dimensional time series and a real-world meteorological dataset; highlighting its practical utility for data assimilation for complex dynamical systems.
- Open Access
- 27 June 2026
- Published by Elsevier in Journal of Theoretical Biology
- Vol. 633, 112544
Joint likelihood-free inference of the number of selected single nucleotide polymorphisms and their selection coefficients in an evolving population
- 27 June 2026
- Published by Elsevier in Journal of Theoretical Biology
- Vol. 633, 112544
Open AccessJoint likelihood-free inference of the number of selected single nucleotide polymorphisms and their selection coefficients in an evolving population
- Open Access
Signature-Informed Selection Detection: A Novel Method for Multi-Locus Temporal Population Genetic Model with Recombination
In population genetics, there is often interest in inferring selection coefficients. This task becomes more challenging if multiple linked selected loci are considered simultaneously. For such a situation, we propose a novel generalized Bayesian framework where we compute a scoring rule posterior for the selection coefficients in multi-locus temporal population genetics models. As we consider trajectories of allele frequencies over time as our data, we choose to use a signature kernel scoring rule - a kernel scoring rule defined for high-dimensional time-series data using iterated path integrals of a path (called signatures). We can compute an unbiased estimate of the signature kernel score using model simulations. This enables us to sample asymptotically from the signature kernel scoring rule posterior of the selection coefficients using pseudo-marginal MCMC-type algorithms. Through a simulation study, we were able to show the inferential efficacy of our method compared to existing benchmark methods for two and three selected locus scenarios under the standard Wright-Fisher model with recombination and selection. We also consider a negative frequency-dependent selection model for one and two locus scenarios, and also joint inference of selection coefficients and initial haplotype frequencies under the standard Wright-Fisher model. Finally, we illustrate the application of our inferential method for two real-life dataset. More specifically, we consider a data set on Yeast, as well as data from an Evolve and Resequence (E\&R) experiment on {\em Drosophila simulans}.
Open AccessSignature-Informed Selection Detection: A Novel Method for Multi-Locus Temporal Population Genetic Model with Recombination
In population genetics, there is often interest in inferring selection coefficients. This task becomes more challenging if multiple linked selected loci are considered simultaneously. For such a situation, we propose a novel generalized Bayesian framework where we compute a scoring rule posterior for the selection coefficients in multi-locus temporal population genetics models. As we consider trajectories of allele frequencies over time as our data, we choose to use a signature kernel scoring rule - a kernel scoring rule defined for high-dimensional time-series data using iterated path integrals of a path (called signatures). We can compute an unbiased estimate of the signature kernel score using model simulations. This enables us to sample asymptotically from the signature kernel scoring rule posterior of the selection coefficients using pseudo-marginal MCMC-type algorithms. Through a simulation study, we were able to show the inferential efficacy of our method compared to existing benchmark methods for two and three selected locus scenarios under the standard Wright-Fisher model with recombination and selection. We also consider a negative frequency-dependent selection model for one and two locus scenarios, and also joint inference of selection coefficients and initial haplotype frequencies under the standard Wright-Fisher model. Finally, we illustrate the application of our inferential method for two real-life dataset. More specifically, we consider a data set on Yeast, as well as data from an Evolve and Resequence (E\&R) experiment on {\em Drosophila simulans}.
- Open Access
Probabilistic Forecasting with Generative Networks via Scoring Rule Minimization
Probabilistic forecasting relies on past observations to provide a probability distribution for a future outcome, which is often evaluated against the realization using a scoring rule. Here, we perform probabilistic forecasting with generative neural networks, which parametrize distributions on high-dimensional spaces by transforming draws from a latent variable. Generative networks are typically trained in an adversarial framework. In contrast, we propose to train generative networks to minimize a predictive-sequential (or prequential) scoring rule on a recorded temporal sequence of the phenomenon of interest, which is appealing as it corresponds to the way forecasting systems are routinely evaluated. Adversarial-free minimization is possible for some scoring rules; hence, our framework avoids the cumbersome hyperparameter tuning and uncertainty underestimation due to unstable adversarial training, thus unlocking reliable use of generative networks in probabilistic forecasting. Further, we prove consistency of the minimizer of our objective with dependent data, while adversarial training assumes independence. We perform simulation studies on two chaotic dynamical models and a benchmark data set of global weather observations; for this last example, we define scoring rules for spatial data by drawing from the relevant literature. Our method outperforms state-of-the-art adversarial approaches, especially in probabilistic calibration, while requiring less hyperparameter tuning.
Open AccessProbabilistic Forecasting with Generative Networks via Scoring Rule Minimization
Probabilistic forecasting relies on past observations to provide a probability distribution for a future outcome, which is often evaluated against the realization using a scoring rule. Here, we perform probabilistic forecasting with generative neural networks, which parametrize distributions on high-dimensional spaces by transforming draws from a latent variable. Generative networks are typically trained in an adversarial framework. In contrast, we propose to train generative networks to minimize a predictive-sequential (or prequential) scoring rule on a recorded temporal sequence of the phenomenon of interest, which is appealing as it corresponds to the way forecasting systems are routinely evaluated. Adversarial-free minimization is possible for some scoring rules; hence, our framework avoids the cumbersome hyperparameter tuning and uncertainty underestimation due to unstable adversarial training, thus unlocking reliable use of generative networks in probabilistic forecasting. Further, we prove consistency of the minimizer of our objective with dependent data, while adversarial training assumes independence. We perform simulation studies on two chaotic dynamical models and a benchmark data set of global weather observations; for this last example, we define scoring rules for spatial data by drawing from the relevant literature. Our method outperforms state-of-the-art adversarial approaches, especially in probabilistic calibration, while requiring less hyperparameter tuning.
- Open Access
- 1 January 2024
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 18 (2) , 3628-3686
Generalized Bayesian likelihood-free inference
Generalized Bayesian inference replaces the likelihood in the Bayesian posterior with the exponential of a loss function connecting parameter values and observations. As a loss function, it is possible to use Scoring Rules (SRs), which evaluate the match between the observation and the probabilistic model for given parameter values. In this work, we leverage this Scoring Rule posterior for Bayesian Likelihood-Free Inference (LFI). In LFI, we can sample from the model but not evaluate the likelihood; hence, we use the Energy and Kernel SRs in the SR posterior, as they admit unbiased empirical estimates. While traditional Pseudo-Marginal (PM) Markov Chain Monte Carlo (MCMC) can be applied to the SR posterior, it mixes poorly for concentrated targets, such as those obtained with many observations. As such, we propose to use Stochastic Gradient (SG) MCMC, which improves performance over PM-MCMC and scales to higher-dimensional setups as it is rejection-free. SG-MCMC requires differentiating the simulator model; we achieve this effortlessly by implementing the simulator models using automatic differentiation libraries. We compare SG-MCMC sampling for the SR posterior with related LFI approaches and find that the former scales to larger sample sizes and works well on the raw data, while other methods require determining suitable summary statistics. On a chaotic dynamical system from meteorology, our method even allows inferring the parameters of a neural network used to parametrize a part of the update equations.
- 1 January 2024
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 18 (2) , 3628-3686
Open AccessGeneralized Bayesian likelihood-free inference
Generalized Bayesian inference replaces the likelihood in the Bayesian posterior with the exponential of a loss function connecting parameter values and observations. As a loss function, it is possible to use Scoring Rules (SRs), which evaluate the match between the observation and the probabilistic model for given parameter values. In this work, we leverage this Scoring Rule posterior for Bayesian Likelihood-Free Inference (LFI). In LFI, we can sample from the model but not evaluate the likelihood; hence, we use the Energy and Kernel SRs in the SR posterior, as they admit unbiased empirical estimates. While traditional Pseudo-Marginal (PM) Markov Chain Monte Carlo (MCMC) can be applied to the SR posterior, it mixes poorly for concentrated targets, such as those obtained with many observations. As such, we propose to use Stochastic Gradient (SG) MCMC, which improves performance over PM-MCMC and scales to higher-dimensional setups as it is rejection-free. SG-MCMC requires differentiating the simulator model; we achieve this effortlessly by implementing the simulator models using automatic differentiation libraries. We compare SG-MCMC sampling for the SR posterior with related LFI approaches and find that the former scales to larger sample sizes and works well on the raw data, while other methods require determining suitable summary statistics. On a chaotic dynamical system from meteorology, our method even allows inferring the parameters of a neural network used to parametrize a part of the update equations.
- Open Access
WITHDRAWN: Signature-Informed Selection Detection: A Novel Method for Multi-Locus Wright–Fisher Models with Recombination
Withdrawal Statement: The authors have withdrawn this manuscript because substantial revisions are required and the authorship contributions have changed. Therefore, the authors do not wish this work to be cited as a reference for the project. If you have any questions, please contact the corresponding author.
Open AccessWITHDRAWN: Signature-Informed Selection Detection: A Novel Method for Multi-Locus Wright–Fisher Models with Recombination
Withdrawal Statement: The authors have withdrawn this manuscript because substantial revisions are required and the authorship contributions have changed. Therefore, the authors do not wish this work to be cited as a reference for the project. If you have any questions, please contact the corresponding author.
- Open Access
- 14 September 2023
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 85 (5) , 1405-1406
David Huk, Lorenzo Pacchiardi, Ritabrata Dutta and Mark Steel's contribution to the Discussion of ‘Martingale posterior distributions’ by Fong, Holmes and Walker
David Huk, Lorenzo Pacchiardi, Ritabrata Dutta, Mark Steel; David Huk, Lorenzo Pacchiardi, Ritabrata Dutta and Mark Steel’s contribution to the Discussion of “M
- 14 September 2023
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 85 (5) , 1405-1406
Open AccessDavid Huk, Lorenzo Pacchiardi, Ritabrata Dutta and Mark Steel's contribution to the Discussion of ‘Martingale posterior distributions’ by Fong, Holmes and Walker
David Huk, Lorenzo Pacchiardi, Ritabrata Dutta, Mark Steel; David Huk, Lorenzo Pacchiardi, Ritabrata Dutta and Mark Steel’s contribution to the Discussion of “M
- Open Access
Generalized Bayesian Likelihood-Free Inference
We propose a posterior for Bayesian Likelihood-Free Inference (LFI) based on generalized Bayesian inference. To define the posterior, we use Scoring Rules (SRs), which evaluate probabilistic models given an observation. In LFI, we can sample from the model but not evaluate the likelihood; hence, we employ SRs which admit unbiased empirical estimates. We use the Energy and Kernel SRs, for which our posterior enjoys consistency in a well-specified setting and outlier robustness. We perform inference with pseudo-marginal (PM) Markov Chain Monte Carlo (MCMC) or stochastic-gradient (SG) MCMC. While PM-MCMC works satisfactorily for simple setups, it mixes poorly for concentrated targets. Conversely, SG-MCMC requires differentiating the simulator model but improves performance over PM-MCMC when both work and scales to higher-dimensional setups as it is rejection-free. Although both techniques target the SR posterior approximately, the error diminishes as the number of model simulations at each MCMC step increases. In our simulations, we employ automatic differentiation to effortlessly differentiate the simulator model. We compare our posterior with related approaches on standard benchmarks and a chaotic dynamical system from meteorology, for which SG-MCMC allows inferring the parameters of a neural network used to parametrize a part of the update equations of the dynamical system.
Open AccessGeneralized Bayesian Likelihood-Free Inference
We propose a posterior for Bayesian Likelihood-Free Inference (LFI) based on generalized Bayesian inference. To define the posterior, we use Scoring Rules (SRs), which evaluate probabilistic models given an observation. In LFI, we can sample from the model but not evaluate the likelihood; hence, we employ SRs which admit unbiased empirical estimates. We use the Energy and Kernel SRs, for which our posterior enjoys consistency in a well-specified setting and outlier robustness. We perform inference with pseudo-marginal (PM) Markov Chain Monte Carlo (MCMC) or stochastic-gradient (SG) MCMC. While PM-MCMC works satisfactorily for simple setups, it mixes poorly for concentrated targets. Conversely, SG-MCMC requires differentiating the simulator model but improves performance over PM-MCMC when both work and scales to higher-dimensional setups as it is rejection-free. Although both techniques target the SR posterior approximately, the error diminishes as the number of model simulations at each MCMC step increases. In our simulations, we employ automatic differentiation to effortlessly differentiate the simulator model. We compare our posterior with related approaches on standard benchmarks and a chaotic dynamical system from meteorology, for which SG-MCMC allows inferring the parameters of a neural network used to parametrize a part of the update equations of the dynamical system.
- Open Access
Bayesian linear models with unknown design over finite alphabets
Our topic is the reconstruction of the unknown matrices S and ω for the multivariate linear model Y = Sω + ε under the assumption that the entries of S are drawn from the finite alphabet 𝔄 = 0, 1 and ω is a weight matrix. While a frequentist method has recently been proposed for this purpose, a Bayesian approach seems also desirable. We therefore provide a new hierarchical Bayesian method for this inferential task. Our approach provides estimates of the posterior that may be used to quantify uncertainty. Since matching permutations in both S and ω lead to the same reconstruction Sω , we introduce an order-preserving shrinkage prior to establish identifiability with respect to permutations.
Open AccessBayesian linear models with unknown design over finite alphabets
Our topic is the reconstruction of the unknown matrices S and ω for the multivariate linear model Y = Sω + ε under the assumption that the entries of S are drawn from the finite alphabet 𝔄 = 0, 1 and ω is a weight matrix. While a frequentist method has recently been proposed for this purpose, a Bayesian approach seems also desirable. We therefore provide a new hierarchical Bayesian method for this inferential task. Our approach provides estimates of the posterior that may be used to quantify uncertainty. Since matching permutations in both S and ω lead to the same reconstruction Sω , we introduce an order-preserving shrinkage prior to establish identifiability with respect to permutations.
- Open Access
Joint likelihood-free inference of the number of selected single nucleotide polymorphisms and the selection coefficient in an evolving population
Given the often intractable exact likelihood, likelihood-free inference plays an important role in population genetics. Indeed, several methodological developments in approximate Bayesian Computation (ABC) were inspired by applications in population genetics. Here, we explore a novel combination of recently proposed ABC tools that can handle high-dimensional summary statistics and apply them to infer selection strength and the number of selected loci from experimental evolution data. While several methods infer selection strength at the single-nucleotide polymorphism (SNP) level, our approach provides additional information about the selective architecture, including the number of selected positions in a candidate window of interest. This is nontrivial, since the spatial correlation induced by genomic linkage can produce selection signals at neighboring SNPs. A further advantage of our approach is that we can readily quantify uncertainty using the ABC posterior. On both simulated and real data, we demonstrate promising performance. This suggests that our ABC variant could also be interesting in other applications.
Open AccessJoint likelihood-free inference of the number of selected single nucleotide polymorphisms and the selection coefficient in an evolving population
Given the often intractable exact likelihood, likelihood-free inference plays an important role in population genetics. Indeed, several methodological developments in approximate Bayesian Computation (ABC) were inspired by applications in population genetics. Here, we explore a novel combination of recently proposed ABC tools that can handle high-dimensional summary statistics and apply them to infer selection strength and the number of selected loci from experimental evolution data. While several methods infer selection strength at the single-nucleotide polymorphism (SNP) level, our approach provides additional information about the selective architecture, including the number of selected positions in a candidate window of interest. This is nontrivial, since the spatial correlation induced by genomic linkage can produce selection signals at neighboring SNPs. A further advantage of our approach is that we can readily quantify uncertainty using the ABC posterior. On both simulated and real data, we demonstrate promising performance. This suggests that our ABC variant could also be interesting in other applications.