iiinova — where your digital self keeps evolving

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/05/2026

The second addresses scalability in simulation-based inference through data reduction, developing methods that learn informative low-dimensional summaries to enable efficient inference in complex settings, with applications to gravitational wave analysis. Keywords: GBI, SBI, amortized learning

010

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/05/2026

We introduce a Bayesian framework for hyperparameter inference using held-out data, enabling coherent estimation and uncertainty quantification, together with amortized generalized-posterior approximations that avoid repeated costly sampling across datasets and hyperparameter values.

110

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/05/2026

Abstract: My talk consists of two parts. The first focuses on Generalised Bayesian Inference (GBI), where the loss hyperparameters are critical under model misspecification yet difficult to determine in a principled way.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/05/2026

The next OWABI seminar www.warwick.ac.uk/owabi of the Season is tomorrow, Thursday the 28th May at 10am UK time. Kate Lee (University of Auckland) will talk about "Towards Robust and Scalable Bayesian Learning". teams.microsoft.com/... Meeting ID: 382 746 871 856 192 Passcode: FZ2gn73K

110

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 20/04/2026

Simulation experiments demonstrate KASPE’s flexibility and performance relative to existing likelihood-free methods including approximate Bayesian computation in challenging inferential settings involving posteriors with heavy tails, multiple local modes, and over the parameters of a nonlinear

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 20/04/2026

simulated datasets. We provide theoretical justification for KASPE and a formal connection to the likelihood-based approach of expectation propagation.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 20/04/2026

We develop an alternative framework called kernel-adaptive synthetic posterior estimation (KASPE) that uses deep learning to directly reconstruct the mapping between the observed data and a finite-dimensional parametric representation of the posterior distribution, trained on a large number of

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 20/04/2026

Fitting these models to data requires likelihood-free inference methods that explore the parameter space without explicit likelihood evaluations, relying instead on sequential simulation, which comes at the cost of computational efficiency and extensive tuning.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 20/04/2026

Abstract: Generative models and those with computationally intractable likelihoods are widely used to describe complex systems in the natural sciences, social sciences, and engineering.

110

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 20/04/2026

MS Teams link: teams.microsoft.com/... Meeting ID: 374 263 351 331 567 Passcode: B8Em6Cg9

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 20/04/2026

The next OWABI seminar www.warwick.ac.uk/owabi is Oksana Chkrebtii (Ohio State University) who will talk about "Likelihood-free Posterior Density Learning for Uncertainty Quantification in Inference Problems" on Thursday the 30th April at 1pm UK time (note the different time!).

112

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 16/03/2026

Finally, we propose two ideas that are useful in the SBI framework beyond robust inference: an SBI based method to obtain closed form approximations of intractable models and an active learning approach to more efficiently sample the parameter space.

arxiv.org

Robust Simulation Based Inference

Simulation-Based Inference (SBI) is an approach to statistical inference where simulations from an assumed model are used to construct estimators and confidence sets. SBI is often used when the...

000

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 16/03/2026

Alternatively, we introduce model expansion through exponential tilting as another way to account for model misspecification. We also develop an SBI based goodness-of-fit test to detect model misspecification.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 16/03/2026

We propose a framework where the target of inference is a projection parameter that minimizes a discrepancy between the true distribution and the assumed model. The method guarantees valid inference, even when the model is incorrectly specified and even if the standard regularity conditions fail.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 16/03/2026

methods or regularity conditions. Traditional SBI methods assume that the model is correct, but, as always, this can lead to invalid inference when the model is misspecified. This paper introduces robust methods that allow for valid frequentist inference in the presence of model misspecification.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 16/03/2026

Abstract: Simulation-Based Inference (SBI) is an approach to statistical inference where simulations from an assumed model are used to construct estimators and confidence sets. SBI is often used when the likelihood is intractable and to construct confidence sets that do not rely on asymptotic

110

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 16/03/2026

The next OWABI seminar www.warwick.ac.uk/owabi will be given by Larry Wasserman (Carnegie Mellon University) who will talk about "Robust Simulation Based Inference" on Wednesday the 25th March at 2pm UK time (note the different day and time!) on Teams teams.microsoft.com/...

120

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 09/03/2026

arxiv.org

Robust Simulation Based Inference

Simulation-Based Inference (SBI) is an approach to statistical inference where simulations from an assumed model are used to construct estimators and confidence sets. SBI is often used when the...

000

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 09/03/2026

We also develop an SBI based goodness-of-fit test to detect model misspecification.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 09/03/2026

The method guarantees valid inference, even when the model is incorrectly specified and even if the standard regularity conditions fail. Alternatively, we introduce model expansion through exponential tilting as another way to account for model misspecification.

110

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 09/03/2026

This paper introduces robust methods that allow for valid frequentist inference in the presence of model misspecification. We propose a framework where the target of inference is a projection parameter that minimizes a discrepancy between the true distribution and the assumed model.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 09/03/2026

SBI is often used when the likelihood is intractable and to construct confidence sets that do not rely on asymptotic methods or regularity conditions. Traditional SBI methods assume that the model is correct, but, as always, this can lead to invalid inference when the model is misspecified.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 09/03/2026

Abstract: Simulation-Based Inference (SBI) is an approach to statistical inference where simulations from an assumed model are used to construct estimators and confidence sets.

110

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 09/03/2026

OWABI⁷, 25 March 2026: Robust Simulation Based Inference (11am UK time) Speaker: Larry Wasserman (Carnegie Mellon University) Title: Robust Simulation Based Inference warwick.ac.uk/fac/sc...

131

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 23/02/2026

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.

000

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 23/02/2026

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.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 23/02/2026

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

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 23/02/2026

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.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 23/02/2026

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.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 23/02/2026

Abstract: Data assimilation is a fundamental task in updating forecasting models upon observing new data, with applications ranging from weather prediction to online reinforcement learning.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 23/02/2026

The next OWABI seminar will be given by Shreya Sinha Roy (Warwick), who will talk about "Prequential posteriors" on Thursday the 26th February at 11am UK time. arxiv.org/abs/2511.1... www.warwick.ac.uk/owabi MS Teams link: teams.microsoft.com/...

arxiv.org

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...

164

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 28/01/2026

or superior performance to existing state-of-the-art methodssuch as Sequential Neural Posterior Estimation (SNPE). Ref: Sharrock, Simons, Liu, Beaumont, Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models. PLMR. openreview.net/pdf?i...

000

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 28/01/2026

the observation of interest, thereby reducing the simulation cost. We also introduce several alternative sequential approaches, and discuss their relative merits. We then validate our method, as well as its amortised, non-sequential, variant on several numerical examples, demonstrating comparable

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 28/01/2026

generate samples from the posterior distribution of interest. The model is trained using an objective function which directly estimates the score of the posterior. We embed the model into a sequential training procedure, which guides simulations using the current approximation of the posterior at

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 28/01/2026

Abstract: We introduce Sequential Neural Posterior Score Estimation (SNPSE), a score-based method for Bayesian inference in simulator-based models. Our method, inspired by the remarkable success of score-based methods in generative modelling, leverages conditional score-based diffusion models to

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 28/01/2026

Tomorrow's OWABI seminar by Louis Sharrock (UCL), who will talk about "Sequential Neural Score Estimation: Likelihood-free inference with conditional score base diffusion models" (29th Jan, 11am UK time). Join: teams.microsoft.com/... Meeting ID: 388 990 396 214 49 Passcode: f3Dh22XL

143

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

Through simulation studies and an application to toad movement models, this work explores whether full data approaches can overcome the limitations of summary statistic-based ABC for model choice. Paper: arxiv.org/abs/2410.2... Teams details: Meeting ID: 365 183 408 357 76 Passcode: 6Fg9nW7T

arxiv.org

Approximate Bayesian Computation with Statistical Distances for...

Model selection is a key task in statistics, playing a critical role across various scientific disciplines. While no model can fully capture the complexities of a real-world data-generating...

000

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

Despite these developments, full data ABC approaches have not yet been widely applied to model selection problems. This paper seeks to address this gap by investigating the performance of ABC with statistical distances in model selection.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

Recent advancements propose the use of full data approaches based on statistical distances, offering a promising alternative that bypasses the need for handcrafted summary statistics and can yield posterior approximations that more closely reflect the true posterior under suitable conditions.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

Approximate Bayesian computation (ABC) has emerged as a likelihood-free method and it is traditionally used with summary statistics to reduce data dimensionality, however this often results in information loss difficult to quantify, particularly in model selection contexts.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

This is typically achieved by calculating posterior probabilities, which quantify the support for each model given the observed data. However, in cases where likelihood functions are intractable, exact computation of these posterior probabilities becomes infeasible.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

Bayesian statistics offers a flexible framework for model selection by updating prior beliefs as new data becomes available, allowing for ongoing refinement of candidate models.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

Abstract: Model selection is a key task in statistics, playing a critical role across various scientific disciplines. While no model can fully capture the complexities of a real-world data-generating process, identifying the model that best approximates it can provide valuable insights.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 17/11/2025

The next OWABI seminar www.warwick.ac.uk/owabi is quickly approaching! Our next speaker is Clara Grazian (Sydney) www.sydney.edu.au/sc..., who will talk about "Approximate Bayesian Computation with Statistical Distances for Model Selection" on 27th Nov, 11am UK time.

110

Reposted by Approximate Bayes Seminar

François-Xavier Briol @fxbriol.bsky.social · 17/11/2025

The recording of my talk on 'Multilevel neural simulation-based inference' at the 'One World Approximate Bayesian Inference' seminar series is now available on YouTube. Link: www.youtube.com/watch?v=hBWd...

youtube.com

François-Xavier Briol: Multilevel neural simulation-Multilevel neural simulation-based inference

YouTube video by ISBA - International Society of Bayesian Analysis

094

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/10/2025

We demonstrate through both theoretical analysis and extensive experiments that our method can significantly enhance the accuracy of SBI methods given a fixed computational budget. The talk will be streamed on MS Teams: Meeting ID: 358 173 458 006 0 Passcode: Vp2975vC

000

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/10/2025

In this paper, we propose a novel approach to neural SBI which leverages multilevel Monte Carlo techniques for settings where several simulators of varying cost and fidelity are available.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/10/2025

However, the performance of neural SBI can suffer when simulators are computationally expensive, thereby limiting the number of simulations that can be performed.

100

Approximate Bayes Seminar @approxbayesseminar.bsky.social · 27/10/2025

Abstract: Neural simulation-based inference (SBI) is a popular set of methods for Bayesian inference when models are only available in the form of a simulator.

110