Paper establishes statistical inference for performative predictions.
problem Dynamic influence of predictions on their targets.
method End-to-end framework for estimation and inference under performativity.
result Established central limit theorem for performative settings.
Proposes TAGI for efficient Gaussian inference in Bayesian neural networks.
problem Efficient inference in Bayesian neural networks with complex architectures.
method Analytical method for tractable approximate Gaussian inference (TAGI).
result Matches performance of gradient-based methods with O(n) computational complexity. Simformer uses transformer models to perform flexible Bayesian inference.
problem Current simulation-based inference methods are inflexible and require fixed priors.
method Trains a probabilistic diffusion model with transformer architectures.
result Outperforms state-of-the-art methods on various benchmarks.
Mobile SoCs can improve ML inference by 2x when all components are used concurrently.
problem Power-performance trade-offs in mobile ML inference on heterogeneous SoCs.
method Quantitative evaluation of different ML components on mobile SoCs.
result Mobile SoCs can achieve up to 2x improvement in inference performance by using all components concurrently.
Thompson Sampling's performance degrades with approximate inference, especially under α-divergence.
problem Thompson Sampling's performance degradation due to approximate inference.
method Study of approximate inference effects on Thompson Sampling in k-armed bandit problems. result Small inference error can lead to poor performance (linear regret) in Thompson Sampling.
CheckNet verifies neural network inference on untrusted devices.
problem Ensuring secure and tamper-proof inference on untrusted devices.
method A checksum-based approach for neural network inference verification.
result Excellent attack detection and success bounds on various models.
New inference method improves performance for probabilistic models with varying support.
problem Existing inference engines for probabilistic programs struggle with models where support varies between executions.
method Divide, Conquer, and Combine (DCC) framework for automated inference.
result Substantial performance improvements on three examples compared to existing approaches.
Metalearned neural circuit performs inference over open classes.
problem Nonparametric Bayesian models' practical barriers in real-world applications.
method Extract inductive bias from nonparametric Bayesian model and transfer to neural network.
result Metalearned neural circuit achieves comparable or better performance than particle filter-based methods.
A new predictive coding algorithm improves machine learning performance.
problem Improving performance of variational inference algorithms in high-dimensional, structured problems.
method Divide-and-Conquer Predictive Coding (DCPC) that respects generative model correlation structure and performs maximum-likelihood updates.
result DCPC achieves better numerical performance and accurate inference in structured generative models.
We present a scalable approach to performing approximate fully Bayesian inference in generic state space models. The proposed method is an alternative to particle MCMC that provides fully Bayesian inference of both the dynamic latent states and the static parameters of the model. We build up on recent advances in compu…
Regularizes sparse Gaussian processes for better model performance.
problem Efficient learning of inducing inputs in latent variable models.
method Proposes a regularization approach to balance reconstruction and approximation performance.
result Improves both inference and prediction performance in latent variable models.
The paper tackles fairness in data and algorithms, expanding on prior work.
problem Discrimination and disparate treatment in data and algorithms.
method Targeted learning for nonparametric inference of fairness in the data generating process.
result Derivation and validation of estimators for fairness metrics like demographic parity and equal opportunity.
We introduce incremental variational inference and apply it to latent Dirichlet allocation (LDA). Incremental variational inference is inspired by incremental EM and provides an alternative to stochastic variational inference. Incremental LDA can process massive document collections, does not require to set a learning …
A benchmark for simulation-based inference methods.
problem Lack of a public benchmark for 'likelihood-free' algorithms.
method Provided a benchmark with tasks and performance metrics, including neural networks and ABC methods.
result State-of-the-art algorithms have room for improvement, and neural network-based approaches generally perform better.
A-NeSI scales approximate inference for probabilistic neurosymbolic learning.
problem Combining neural networks with symbolic reasoning for scalable inference.
method A-NeSI: a new framework for PNL using neural networks for approximate inference.
result A-NeSI achieves scalable approximate inference without semantic changes.
The emerging paradigm of Human-Machine Inference Networks (HuMaINs) combines complementary cognitive strengths of humans and machines in an intelligent manner to tackle various inference tasks and achieves higher performance than either humans or machines by themselves. While inference performance optimization techniqu…
Energy savings for DNN inference on resource-constrained devices.
problem Energy efficiency in deep learning inference for constrained devices.
method Efficiently searches through equivalent DNN graphs to find the one with the least execution cost.
result Achieves 24% energy savings with minimal performance impact.
We extend the existing framework of semi-implicit variational inference (SIVI) and introduce doubly semi-implicit variational inference (DSIVI), a way to perform variational inference and learning when both the approximate posterior and the prior distribution are semi-implicit. In other words, DSIVI performs inference …
NeuZip compresses neural network weights to save memory during training and inference.
problem Memory constraints in neural network training and inference.
method Entropy-based dynamic weight compression.
result Significant reduction in memory usage without performance loss.
The variational autoencoder (VAE) is a popular model for density estimation and representation learning. Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate. However, it is often overlooked that an overly-expressive inference model ca…
APT improves likelihood-free inference by dynamically transforming posterior estimates.
problem Performing Bayesian inference on simulators with intractable likelihoods.
method Automatic posterior transformation (APT) using neural network-based density estimators.
result APT is more flexible, scalable, and efficient than previous methods.
BayesFlow trains neural networks for fast Bayesian inference.
problem Fast Bayesian inference for complex models.
method Amortized neural networks for intractable posterior distributions.
result Fast inference through pre-trained neural networks.
Method infers parameters in complex diffusion processes.
problem Parameter inference in high-dimensional, non-linear diffusion processes.
method Differentiable score matching to approximate diffusion bridges, used in an importance sampler.
result Numerically stable framework for parameter inference and diffusion mean estimation.
A Closer Look at Disentangling in β-VAE shows non-monotonic inference performance.
problem Learning disentangled representations from data.
method Generalization of VAE using variational inference with hyperparameter β.
result Non-monotonic inference performance in β-VAE with a finite optimal β.
GATSBI uses GANs for SBI, improving posterior estimation in high dimensions.
problem Statistical inference on stochastic models without likelihoods.
method Adversarial approach to variational objective, amortized inference, implicit priors.
result GATSBI returns well-calibrated posterior estimates in high dimensions.
Causal inference from observational data often assumes "ignorability," that all confounders are observed. This assumption is standard yet untestable. However, many scientific studies involve multiple causes, different variables whose effects are simultaneously of interest. We propose the deconfounder, an algorithm that…
Etalumis bridges scientific simulators and probabilistic programming.
problem Infeasibility of rewriting scientific simulators for Bayesian inference.
method Cross-platform probabilistic execution protocol, MCMC and IC engines, distributed training of 3DCNN-LSTM.
result Achieved largest-scale posterior inference in a Turing-complete PPL for LHC use-case.
Improved Bayesian neural network inference by selectively removing redundant modes.
problem Redundant modes in Bayesian neural network posteriors complicate approximate inference.
method Structured partial stochasticity and deterministic subset selection of weights.
result Improved performance of approximate inference schemes with simplified posterior distribution.
Convolutional neural networks learn effective summary statistics for ABC inference.
problem Selecting high-quality summary statistics for accurate ABC inference in complex systems.
method Proposes a CNN architecture to automatically learn informative summary statistics from time series data.
result CNNs can effectively circumvent the statistics selection problem in ABC inference.
AGMs outperform EGMs in generalizing to unseen inference tasks.
problem Training graphical models for inference tasks not seen during training.
method Adversarial training of an ensemble of discrete graphical models.
result AGMs significantly outperform EGMs in generalization to unseen tasks.
Algorithm optimizes and infers performance online, improving reliability.
problem Balancing optimization and statistical inference in complex systems.
method Online algorithm that provides consistent performance variance and confidence intervals.
result Online consistent estimator for performance variance and asymptotic confidence intervals.
Method infers causal direction using data discretization and complexity calculation.
problem Determining causal direction between continuous variables.
method MDL Binning technique for data discretization and complexity calculation.
result Captures the shape of the data to determine causal direction.
Probabilistic inference procedures are usually coded painstakingly from scratch, for each target model and each inference algorithm. We reduce this effort by generating inference procedures from models automatically. We make this code generation modular by decomposing inference algorithms into reusable program-to-progr…
GWI combines deep neural networks with Gaussian processes for better predictive performance and uncertainty quantification.
problem Combining deep learning with Gaussian process uncertainty quantification.
method Gaussian Wasserstein inference (GWI) using Wasserstein distance between Gaussian measures.
result GWI achieves state-of-the-art performance on benchmark datasets.
New algorithm improves inference-time alignment without reward hacking.
problem Improving quality of responses from language models with limited compute.
method Inference-time alignment, focusing on extttInferenceTimePessimism algorithm. result Optimal performance and scaling-monotonicity of extttInferenceTimePessimism. DDVI uses diffusion models for variational inference, improving latent variable model performance.
problem Improving variational inference in latent variable models.
method Introduces diffusion-based variational posteriors trained with a regularized ELBO.
result Outperforms alternative variational posteriors on various benchmarks and a biology task.
New coin sampling method for Bayesian inference without learning rates.
problem Scalable Bayesian inference with learning rate tuning issues.
method Coin sampling for gradient-based Bayesian inference.
result Comparable performance to other ParVI algorithms without learning rate tuning.
New method improves robustness and efficiency of inference from complex models.
problem Inability of existing methods to handle outliers in simulator-based models.
method Generalised Bayesian inference with neural approximation of weighted score-matching loss.
result Provable robustness to outliers and computational efficiency.
Variational inference improves neural network matrix factorization for stochastic blockmodels.
problem Improving predictive performance of neural network matrix factorization for stochastic blockmodels.
method Construct Bayesian neural networks and fit with variational inference.
result Variational inference can achieve equivalent performance to neural networks on Movielens data.
MLPerf benchmarks ML inference systems across diverse hardware.
problem Challenges in evaluating ML inference systems due to variety and complexity.
method MLPerf prescribes a set of rules and best practices for comparability.
result First call for submissions yielded over 600 reproducible measurements.
TSNPE improves SBI efficiency and scalability.
problem Efficient and scalable simulation-based inference for complex models.
method Sequential inference with truncated proposals.
result TSNPE performs on par with previous methods and scales to complex models.
Inferring the structure of gene regulatory networks (GRN) from gene expression data has many applications, from the elucidation of complex biological processes to the identification of potential drug targets. It is however a notoriously difficult problem, for which the many existing methods reach limited accuracy. In t…
InfoSEM infers gene regulatory networks without GT labels, improving performance.
problem Inferring GRNs from gene expression data with high accuracy and avoiding biases.
method InfoSEM uses deep generative models with informative priors (textual gene embeddings).
result InfoSEM outperforms existing models by 38.5% across four datasets.
Matched Machine Learning combines machine learning and matching for causal inference.
problem Non-interpretable methods for causal inference.
method Combines machine learning and matching for interpretable causal inference.
result Performs as well as black-box machine learning methods and better than existing matching methods.
Paper introduces a diagnostic for approximate inference methods.
problem Estimating errors in probabilistic inference algorithms, especially for approximate methods.
method Repeatedly simulate datasets from the prior and perform inference on each, estimating a symmetric KL-divergence.
result A diagnostic for approximate inference methods can be estimated using symmetric KL-divergence.
L-HNNs improve Bayesian inference efficiency by reducing gradient computation.
problem Efficient Bayesian inference with minimal gradient computation.
method Integrating L-HNNs into NUTS with online error monitoring.
result L-HNNs in NUTS outperform NUTS in complex posterior densities.
Proposes OpenKI for better web-scale knowledge extraction and alignment.
problem Combining OpenIE and KB for web-scale knowledge extraction and alignment.
method Instance-level inference using neighborhood information from KB and OpenIE extractions, with attention mechanisms.
result Significantly improves performance on OpenIE extractions and semi-structured data.
We introduce the variational filtering EM algorithm, a simple, general-purpose method for performing variational inference in dynamical latent variable models using information from only past and present variables, i.e. filtering. The algorithm is derived from the variational objective in the filtering setting and cons…