Bayesian inference
PulseAugur coverage of Bayesian inference — every cluster mentioning Bayesian inference across labs, papers, and developer communities, ranked by signal.
- used by Markov chain Monte Carlo 70%
- instance of Markov chain Monte Carlo 70%
- instance of alphaXiv 70%
- used by alphaXiv 60%
- instance of Gotit.pub 60%
- instance of ScienceCast 60%
- used by Normalizing Flows 60%
- uses Normalizing Flows 60%
- other ScienceCast 50%
- used by Gotit.pub 50%
- used by ScienceCast 50%
- other Influence Flower 50%
5 day(s) with sentiment data
-
LLMs show data-efficient numerical prediction using semantic grounding · arXiv paper
A new arXiv paper demonstrates that large language models (LLMs) can perform numerical prediction on tabular data with remarkable data efficiency. By leveraging semantic grounding, which aligns variable names with their…
-
LLMs' reasoning questioned: Do they follow Bayesian principles?
Large Language Models (LLMs) exhibit a tendency to interpret plausible counterarguments as supporting evidence for their own conclusions, rather than objectively evaluating them against expected information. This behavi…
-
New framework models Bayesian inference in game theory dynamics
A new paper on arXiv introduces Bayesian Replicator Dynamics, a framework that models agents learning through trial and error and also serves as a method for continuous-time Bayesian inference. The research categorizes …
-
New methods improve Bayesian inference for agent-based models
Researchers have developed new methods for Bayesian inference in agent-based models (ABMs), which are commonly used in economics and social sciences. The first paper introduces a framework called sequential neural poste…
-
LLMs show improved Bayesian inference with code execution
Researchers have developed a new evaluation framework to test the Bayesian inference capabilities of large language models (LLMs). The framework assesses LLMs' ability to update beliefs in context, a crucial aspect of s…
-
New GBOED framework enhances experimental design robustness
Researchers have introduced Generalised Bayesian Optimal Experimental Design (GBOED), a novel framework that enhances the robustness of experimental design and inference. GBOED extends generalized Bayesian inference by …
-
New model frames spatial hearing using free energy principle
Researchers have developed a hierarchical generative model to frame spatial hearing within the free energy principle (FEP). This model characterizes how listeners' beliefs about sound direction evolve based on visual fe…
-
New Bayesian inference method uses neural estimators for complex models
Researchers have developed a new semi-amortized Bayesian inference method that breaks down high-dimensional models into smaller blocks. This approach uses neural estimators to approximate conditional posteriors for bloc…
-
New research explores training-free LLM preference learning methods · 2 sources tracked
Two new research papers explore methods for improving how large language models (LLMs) handle sequential preference learning without requiring extensive fine-tuning. The first paper, "AdaptFuse," introduces a training-f…
-
New Bouncy Particle Sampler Enhances Sampling Efficiency for Complex Distributions
Researchers have developed a new method called Bouncy Particle Sampler with Parallel Tempering (BPS-PT) to improve sampling efficiency from complex probability distributions. This technique builds upon the Bouncy Partic…
-
New Reweighted ALPS method improves multimodal distribution sampling
Researchers have developed a new method called Reweighted ALPS (Re-ALPS) to improve sampling from multimodal distributions, a common challenge in Bayesian inference and machine learning. This technique aims to overcome …
-
New Measure Neural Mappings Enhance AI for Scientific Learning
Researchers have introduced Measure Neural Mappings (MNMs), a novel approach that combines measure-dependent neural transport with ensemble consistency for learning operators on probability measures. This method is part…
-
New NFDiag method enhances MCMC convergence diagnosis in high dimensions
Researchers have introduced NFDiag, a novel method for diagnosing the convergence of Markov chain Monte Carlo (MCMC) simulations, particularly in high-dimensional scenarios. Unlike traditional diagnostics that focus on …
-
New research reveals spectral structures within Prior-Data Fitted Networks
Two new research papers explore the internal mechanisms of Prior-Data Fitted Networks (PFNs), a type of tabular foundation model. The first paper provides mechanistic evidence that PFNs capture spectral structures relat…
-
New method enhances AI uncertainty quantification for neural networks
Researchers have developed a novel method for scalable uncertainty quantification in neural networks, crucial for high-stakes AI applications. Their approach, termed generalized Laplace active subspaces, constructs a lo…
-
Yudkowsky Explores Robin Hanson's Bayesian Update Concept
Eliezer Yudkowsky's article on LessWrong discusses the concept of "Bayesians Don't Predictably Update," attributing its popularization to Robin Hanson. The piece delves into the implications of this idea within the fram…
-
New method Causal Posterior Estimation improves Bayesian inference
Researchers have introduced Causal Posterior Estimation (CPE), a new technique for Bayesian inference in complex simulator models. CPE utilizes flow matching to approximate posterior distributions, crucially integrating…
-
New Spectra method adapts AI inference models to updated prior information
Researchers have developed Spectra, a novel method for adapting simulation-based inference (SBI) models to new prior distributions at test time. This technique, detailed in a recent arXiv paper, utilizes an exact score-…
-
Deep neural networks offer new approach to quantum parameter estimation with uncertainty quantification
A new research paper introduces deep ensembles, a type of neural network, for quantum parameter estimation. This method not only provides accurate parameter estimates but also quantifies uncertainty, a feature often los…
-
New Bayesian inference methods improve simulation-based calibration for complex models
Researchers have developed new methods for simulation-based Bayesian inference (SBI) for models with intractable likelihoods but tractable forward simulation. The first contribution introduces a sequential procedure usi…