We develop a new method to estimate failure probabilities in complex systems.
problem Estimating failure probabilities in safety-critical autonomous systems is challenging due to the rarity of failures and large state spaces.
method We propose an adaptive importance sampling algorithm that minimizes forward Kullback-Leibler divergence and uses Markov score ascent methods.
result Our method provides more accurate failure probability estimates than existing techniques.
BIS uses bandits to efficiently sample from expensive-to-evaluate densities.
problem Sampling from computationally expensive target densities.
method Sequential selection through multi-armed bandits, optimizing sample set directly.
result BIS achieves accurate sampling with fewer evaluations than adaptive methods.
Paper improves VAEs using Monte Carlo methods.
problem Improving the Evidence Lower Bound (ELBO) for VAEs.
method Uses Monte Carlo techniques to improve ELBO, specifically Sequential Importance Sampling (SIS) with carefully chosen kernels.
result Demonstrates improved performance on various applications.
A training-free method for conditional sampling using flow matching.
problem Weight degeneracy in high-dimensional importance sampling.
method Sequential Monte Carlo with resampling and stochastic flow.
result Significantly outperforms existing methods on MNIST and CIFAR-10.
VISA improves inference efficiency for complex models.
problem Efficient approximate inference in computationally intensive models.
method Sequential sample-average approximations within a trust region.
result VISA achieves comparable accuracy with computational savings.
DAIS improves AIS by resampling, avoiding gradient issues.
problem Low effective sample size in DAIS.
method DAIS with resampling step to improve efficiency.
result Resampling step avoids gradient variance issues.
A new method uses ABC-SMC to infer hybrid models in bioprocesses with limited data.
problem Inference of hybrid models in bioprocesses with limited real data and high uncertainties.
method Approximate Bayesian Computation with Sequential Monte Carlo (ABC-SMC) and linear Gaussian dynamic Bayesian network (LG-DBN) for posterior distribution approximation.
result The method accelerates hybrid model inference and supports process monitoring and robust control.
AFT combines AIS, SMC, and NFs for better Monte Carlo estimates.
problem Estimating normalizing constants of complex probability distributions.
method Annealed Flow Transport (AFT) integrates AIS, SMC, and normalizing flows.
result AFT improves Monte Carlo estimates of normalizing constants and expectations.
Efficiently estimates online variational learning using importance sampling.
problem Online variational estimation in state-space models.
method Variational approach with Monte Carlo importance sampling.
result Proposed efficient algorithm for streaming data.
Combines control variates and adaptive importance sampling for Monte Carlo integration.
problem Improving Monte Carlo integration accuracy with control variates and adaptive sampling.
method A quadrature rule combining control variates and adaptive importance sampling.
result Non-asymptotic bound on the probabilistic error of the procedure.
Tensor Monte Carlo improves variational autoencoders for high-dimensional latent spaces.
problem Scalability issues in IWAEs for high-dimensional latent spaces.
method Tensor Monte Carlo (TMC) draws exponentially many samples separately for each latent variable and averages them.
result TMC outperforms IWAE on a generative model with multiple stochastic layers.
Recently, it has been shown how sampling actions from the predictive distribution over the optimal action-sometimes called Thompson sampling-can be applied to solve sequential adaptive control problems, when the optimal policy is known for each possible environment. The predictive distribution can then be constructed b…
The paper bounds the error of SMC samplers using probabilistic programming.
problem Quantifying the error of SMC samplers that are far from the target posterior.
method Upper-bounds the symmetric KL divergence using a gold-standard sampler.
result The method applies to various SMC samplers and estimates their divergence bounds.
New method improves Monte Carlo sampling efficiency.
problem Efficiently approximating posterior distributions.
method Group Importance Sampling (GIS) for particle filtering and MCMC.
result GIS improves upon existing Monte Carlo techniques.
ABC Samplers detail methods for sampling from ABC approximations.
problem Sampling from ABC approximations to posterior distributions.
method Rejection/importance sampling, MCMC, sequential Monte Carlo.
result Various ABC sampling methods are detailed and compared.
Paper proposes a new method for sampling from complex distributions.
problem Sampling from unnormalised density functions in complex distributions.
method Combines amortised and particle-based methods with reinforcement learning.
result Improves sampling from complex distributions compared to existing methods.
The paper emphasizes the importance of joint predictions over marginal predictions for decision-making.
problem The need for accurate joint predictions in decision-making problems.
method The paper analyzes combinatorial decision problems, sequential predictions, and multi-armed bandits, introducing an approximate Thompson sampling algorithm and new regret bounds.
result Accurate joint predictions are essential for good performance in decision-making problems.
Sequential Monte Carlo techniques are useful for state estimation in non-linear, non-Gaussian dynamic models. These methods allow us to approximate the joint posterior distribution using sequential importance sampling. In this framework, the dimension of the target distribution grows with each time step, thus it is nec…
Sampling is an important tool for estimating large, complex sums and integrals over high dimensional spaces. For instance, important sampling has been used as an alternative to exact methods for inference in belief networks. Ideally, we want to have a sampling distribution that provides optimal-variance estimators. In …
Improved variational inference for GPLVMs using AIS.
problem Challenges in generating effective proposal distributions for high-dimensional or complex data.
method Annealed Importance Sampling (AIS) combined with reparameterization.
result Our method achieves tighter variational bounds and higher log-likelihoods.
Kernel Quadrature improves numerical integration with adaptive tempering.
problem Optimizing sampling distribution for Kernel Quadrature to reduce integration error.
method Adaptive tempering and sequential Monte Carlo approach to find optimal sampling distribution.
result Significant reduction in integration error (up to 4 orders of magnitude) achieved with the proposed method.
The paper uses Bayesian methods to infer hidden processes with unknown parameters.
problem Estimating hidden processes from noisy observations with unknown parameters.
method Variational Bayesian inference with autoregressive moving average (ARMA) and vector autoregressive (VAR) models, combined with sequential Monte Carlo (SMC) and importance sampling resampling (SISR).
result The proposed inference method accurately estimates hidden states from non-linear noisy observations.
GUESS improves surrogate model accuracy with adaptive sampling.
problem Creating accurate surrogate models with limited data.
method Gradient and Uncertainty Enhanced Sequential Sampling (GUESS) using predictive uncertainty and Taylor expansion.
result GUESS achieved highest sample efficiency compared to other strategies.
Parallelizes active learning for Bayesian inference using Nested Sampler.
problem Expensive likelihood evaluations in complex experiments.
method Uses Nested Sampler to generate nearly-optimal batches of candidates in parallel.
result Comparable accuracy to sequential conditioning with efficient parallelization.
Optimal tests developed for sequential experiments with asymptotic properties.
problem Performing hypothesis tests after sequential experiments without prior design.
method Analyze asymptotic properties of sequential experiments; develop tests for Gaussian process observations.
result Asymptotic power function of any test can be matched by a specific test in a limit experiment.
Efficiently estimates marginal likelihood using SGAIS.
problem Estimating marginal likelihood in i.i.d. data settings.
method Stochastic Gradient Annealed Importance Sampling (SGAIS).
result Significantly faster and more accurate estimates of marginal likelihood.
Pricing options is an important problem in financial engineering. In many scenarios of practical interest, financial option prices associated to an underlying asset reduces to computing an expectation w.r.t.~a diffusion process. In general, these expectations cannot be calculated analytically, and one way to approximat…
New method for mixed data FI controls type I error and achieves high power.
problem Statistical inadequacy of feature importance measures for mixed data.
method Combining CPI framework with sequential knockoffs for mixed data.
result Our method controls type I error and achieves high power for mixed data.
Improves off-policy RL stability with RIS.
problem Stability issues in off-policy RL due to distributional mismatch.
method Relative Importance Sampling (RIS) for off-policy actor-critic.
result RIS stabilizes RL learning by reducing variance.
Variable selection for optimal treatment regime in a clinical trial or an observational study is getting more attention. Most existing variable selection techniques focused on selecting variables that are important for prediction, therefore some variables that are poor in prediction but are critical for decision-making…
LF-IBIS learns optimal policies online without explicit likelihood.
problem Bayesian RL challenges due to intractable likelihood functions.
method Combines ABC with IBIS for online belief updates.
result Approximates posterior distributions for policies and parameters.
Method uses neural networks to speed up probabilistic model inference.
problem Efficient inference in probabilistic models.
method Compiles probabilistic programs into neural networks for approximate inference.
result Significant speedups in inference efficiency demonstrated on various models.
This paper simplifies OPE in large state spaces using state abstractions.
problem Accurately evaluating policies offline in large state spaces.
method Developed a backward-model-irrelevance condition and an iterative state abstraction procedure.
result Deeply-abstracted states substantially simplify OPE sample complexity.
Study rare-event simulation for neural networks and random forests.
problem Safety evaluation and robustness quantification of machine learning models.
method Importance sampling scheme integrating large deviations and sequential mixed integer programming.
result Efficiency guarantees and numerical demonstrations for various neural network architectures.
The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.
problem Understanding why history-dependent policies can improve MSE in off-policy evaluation.
method The paper derives a bias-variance decomposition of MSE for various OPE estimators, showing how history-dependent policies can decrease variance and increase bias.
result History-dependent policies can decrease the variance of importance sampling estimators, leading to lower MSE.
Improved particle pricing methods for path-dependent options.
problem Efficient simulation of spot price and volatility for path-dependent options.
method Sequential Monte Carlo with branching and resampling.
result Branching algorithms improve pricing performance for path-dependent options.
Efficiently samples latent functions in complex data models with sequential structure.
problem Inference of latent functions in probabilistic models with complex data likelihoods.
method Extends Markov chain Monte Carlo techniques to handle sequential structure, enabling efficient sampling of latent variables and parameters.
result Strong performance in growing-data settings, demonstrating scalability.
Persistent sampling improves SMC efficiency by retaining and reusing particles.
problem High computational costs and particle impoverishment in SMC.
method Persistent sampling (PS) retains and reuses particles from all prior iterations, using multiple importance sampling and resampling from a mixture of historical distributions.
result PS achieves more accurate posterior approximations and lower variance in marginal likelihood estimates without additional likelihood evaluations.
New insights on bias in multi-armed bandits under conditional sampling.
problem Understanding bias in multi-armed bandits under conditional sampling.
method Characterized the sign of conditional bias of monotone functions of rewards.
result Sign of conditional bias can differ from marginal bias, depending on conditioning events.
CRAFT improves on existing methods for sampling complex distributions.
problem Sampling from complex probability distributions.
method Combines SMC with variational inference using normalizing flows.
result Improves on Annealed Flow Transport Monte Carlo and MCMC-based Stochastic Normalizing Flows.
Clustering with fast algorithms large samples of high dimensional data is an important challenge in computational statistics. Borrowing ideas from MacQueen (1967) who introduced a sequential version of the k-means algorithm, a new class of recursive stochastic gradient algorithms designed for the k-medians loss cri…
Study evaluates CL methods in RNNs, highlighting differences from feedforward networks.
problem Preventing catastrophic forgetting in RNNs processing sequential data.
method Comprehensive evaluation of CL methods, including elastic weight consolidation and hypernetworks.
result Weight-importance methods perform similarly regardless of sequence length but require more stability for high working memory demands.
LEAPS samples discrete distributions via CTMCs and locally equivariant networks.
problem Sampling from discrete distributions with known normalization.
method Continuous-time Markov chain, locally equivariant functions, attention layers, convolutional networks.
result LEAPS minimizes the variance of importance weights, improving sampling efficiency.
Survey categorizes methods for learning state representations in reinforcement learning.
problem Addressing challenges in complex observation spaces for sequential decision making.
method Categorizes six main classes of methods for learning state representations.
result Enhances understanding of state representation learning in reinforcement learning.
Stochastic WaveNet models sequential data with latent variables and dilated convolutions.
problem Modeling distribution of sequential data like speech and motions.
method Combines stochastic latent variables and dilated convolutions in WaveNet architecture.
result Obtains state-of-the-art performances on speech and handwriting datasets.
OASIS optimizes ER evaluation by reducing labelling needs with optimal sampling.
problem Extreme class imbalance in ER leads to high labelling costs.
method OASIS uses a biased instrumental distribution and Bayesian updates to focus on unlabelled items.
result OASIS estimates F-measure, precision, recall converge to true values with significant labelling reductions.
Paper analyzes Nyström regularization for time series forecasting with sequential sub-sampling.
problem Learning rate analysis of Nyström regularization for τ-mixing time series. method Banach-valued Bernstein inequality and integral operator approach for τ-mixing sequences. result Almost optimal learning rates for Nyström regularization with sequential sub-sampling.
Kernel adaptive filters (KAF) are a class of powerful nonlinear filters developed in Reproducing Kernel Hilbert Space (RKHS). The Gaussian kernel is usually the default kernel in KAF algorithms, but selecting the proper kernel size (bandwidth) is still an open important issue especially for learning with small sample s…