25 papers · 1 filter
Large Language Bayes Is Not Reparameterisation-Invariant
Jian Xu
Large Language Bayes (LLB) answers an informal modelling question by sampling candidate probabilistic programs from a language model, running approximate inference on each, and ave…
Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation
Jian Xu, Delu Zeng, John Paisley
Joint audio--video (AV) generators are trained on data in which \emph{what an event looks like} and \emph{what it sounds like} are spuriously correlated. We present a \emph{control…
Mode Collapse Is Cheap to Detect: A Ground-Truth-Free Pre-Flight Check for Neural Samplers
Jian Xu
Neural samplers are trained against an unnormalised target with no samples from , which leaves the practitioner with no way to tell whether an expensive trainin…
Partially Observed Sparse Graphs: The Unknown Sampling Rate is a Tail Index
Jian Xu, Delu Zeng, John Paisley +1
A large graph is often available only in part: a crawl stopped by its budget, a panel, a partial dump. When the sampled fraction is known by design the total edge count follows…
Evaluating Generative Time-Series Models on Data with Point Masses
Jian Xu
Many of the series that generative time-series models are benchmarked on place a large probability mass on a single value --- it does not rain, no ride is requested, no part is ord…
When Can You Debias an LLM Judge? Identifiability Limits, a Test, and Designs for Top-k Ranking
Jian Xu, Delu Zeng, John Paisley +1
Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise. Because such judges prefer verbose or well-formatted answers,…
Active Quantum Kernel Acquisition for Gaussian Process Regression
Jian Xu, Artur Miroszewski, John Paisley +2
Quantum kernel estimation on near-term hardware is shot-budgeted: every entry of the kernel Gram matrix is a Bernoulli expectation that must be sampled with a finite number of circ…
Calibration, Not Compilation: Detecting and Repairing Misspecified Probabilistic Programs Written by Language Models
Jian Xu, Delu Zeng, John Paisley +1
Language models increasingly write probabilistic programs (in NumPyro, Stan, or Pyro), but a program that compiles, runs, and passes every unit test can still be \emph{statisticall…
Intrinsic Flow Matching on Quantum Pure-State Manifolds with Phase-Aligned Transport
Jian Xu, Delu Zeng, John Paisley +1
Quantum pure-state ensembles live on complex projective space, making flat Euclidean generative modeling geometrically mismatched. We introduce Intrinsic Flow Matching (IFM), a det…
Effective Dimension Governs Generalization in Quantum Kernel Vision Models
Jian Xu, Delu Zeng, John Paisley +1
Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more…
Implicit Variational Rejection Sampling
Jian Xu, Shigui Li, Wei Chen +6
Variational Inference (VI) is a fundamental inference technique in Bayesian machine learning for approximating complex posterior distributions. Traditional VI often relies on the m…
The Right Measure for Physics-Constrained Generation: A Co-Area Correction for Posterior-Consistent PDE Inverse Problems
Jian Xu, Yanning Wu, Delu Zeng +2
Generative models -- diffusion and flow matching -- are increasingly used to solve partial differential equation (PDE) inverse problems, enforcing the governing physics as a \emph{…
Spectral Anatomy of Quantum Gaussian Process Kernels
Jian Xu, Chao Li, Guang Lin +4
Two recent results have reshaped quantum Gaussian processes (QGPs). On the one hand, \citet{lowe2025assessing} rule out the exponential speedups claimed by HHL-based QGP regression…
On the Approximation Complexity of Matrix Product Operator (MPO) Born Machines
Chao Li, Zerui Tao, Yuchen Cong +2
Matrix product operator Born machines (MPO-BMs) are tractable tensor-network models for probabilistic modeling, yet their approximation capabilities remain poorly understood in the…
AQKA: Active Quantum Kernel Acquisition Under a Shot Budget
Jian Xu, Chao Li, Delu Zeng +2
Estimating an quantum kernel from circuit fidelities requires measurement shots, the dominant bottleneck for deployment on near-term hardware. Existing budg…
Diffusion Bridge Variational Inference for Deep Gaussian Processes
Jian Xu, Qibin Zhao, John Paisley +1
Deep Gaussian processes (DGPs) enable expressive hierarchical Bayesian modeling but pose substantial challenges for posterior inference, especially over inducing variables. Denoisi…
Neural Bridge Processes
Jian Xu, Yican Liu, Delu Zeng +2
Learning stochastic functions from partially observed context-target pairs requires models that are expressive, uncertainty-aware, and strongly conditioned on inputs. Neural Diffus…
Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
Jian Xu, Zhiqi Lin, Shigui Li +4
Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However,…
Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Sampling
Jian Xu, Shian Du, Junmei Yang +3
Gaussian Process Latent Variable Models (GPLVMs) have become increasingly popular for unsupervised tasks such as dimensionality reduction and missing data recovery due to their fle…
Sparse Variational Student-t Processes for Heavy-tailed Modeling
Jian Xu, Delu Zeng, John Paisley
The Gaussian process (GP) is a powerful tool for nonparametric modeling, but its sensitivity to outliers limits its applicability to data distributions with heavy-tails. Studentt p…
Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations
Jian Xu, Zhiqi Lin, Min Chen +3
Deep Gaussian process models typically employ discrete hierarchies, but recent advancements in differential Gaussian processes (DiffGPs) have extended these models to infinite dept…
Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference
Jian Xu, Delu Zeng, John Paisley
Deep Gaussian processes (DGPs) provide a robust paradigm for Bayesian deep learning. In DGPs, a set of sparse integration locations called inducing points are selected to approxima…
Sparse Variational Student-t Processes
Jian Xu, Delu Zeng
The theory of Bayesian learning incorporates the use of Student-t Processes to model heavy-tailed distributions and datasets with outliers. However, despite Student-t Processes hav…
Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes
Jian Xu, Shian Du, Junmei Yang +2
Deep Gaussian Process (DGP) models offer a powerful nonparametric approach for Bayesian inference, but exact inference is typically intractable, motivating the use of various appro…