This paper explores Bayesian Neural Network posteriors, uncovering symmetries and their impact.
problem Understanding the complex posterior distribution of deep Bayesian Neural Networks.
method Investigates optimal approaches for approximating posteriors, analyzes modes, and explores visualizations.
result Uncovered weight-space symmetries and their impact on the posterior, particularly scaling symmetries.
New method uses RRTs to explore Bayesian NMF more effectively.
problem Slow mixing and mode sticking in Bayesian NMF.
method Rapidly exploring random trees (RRTs) in a Bayesian framework.
result Greater coverage of the posterior and higher ELBO values.
GPPSTD uses Gaussian Processes for efficient RL in continuous states.
problem Efficient reinforcement learning in continuous state spaces.
method Gaussian Process Posterior Sampling Reinforcement Learning (GPPSTD) algorithm.
result Combining demonstration and exploration improves reinforcement learning efficiency.
Enhanced Gaussian process models accelerate optimization and posterior approximation.
problem Improving the accuracy and speed of Gaussian process models for optimization and inference.
method Introduces a random exploration step to classical GP-UCB algorithms, facilitating faster convergence.
result New algorithms achieve nearly optimal convergence rates and provide bounds for Hellinger distance.
S-VBMC improves VBMC's exploration of complex posterior distributions.
problem Efficient inference for computationally expensive models with complex posterior distributions.
method Stacking multiple independent VBMC runs to create a robust global posterior approximation.
result Significant improvements in posterior approximation quality across various applications.
HyperAgent improves RL exploration in large-scale problems.
problem Efficient exploration in large-scale reinforcement learning problems.
method Hypermodel framework for incremental posterior approximation without conjugacy.
result HyperAgent achieves logarithmic per-step computational complexity and sublinear regret.
Deep Bayesian Bandits compare methods for balancing exploration and exploitation in complex domains.
problem Balancing exploration and exploitation in complex sequential decision-making problems.
method Benchmarking approximate Bayesian neural networks with Thompson Sampling over contextual bandit problems.
result Many approaches successful in supervised learning underperform in sequential decision-making.
Improved sampling for multimodal posterior distributions using stochastic gradient methods.
problem Inadequate exploration of multimodal posterior distributions in stochastic gradient MCMC.
method Proposes a generalized kinetic function for Hamiltonian Monte Carlo to enhance mixing in stochastic gradient MCMC.
result Demonstrates superior exploration of complex multimodal posterior distributions.
Study improves posterior inference in neural processes with limited data.
problem Improving posterior predictive inference in probabilistic models with scarce conditioning data.
method Examined effects of pooling operators and variational families on posterior quality in neural processes.
result Novel neural process architectures lead to superior posterior predictive samples in image completion/in-painting tasks.
The cold posterior effect is explored through PAC-Bayes bounds for small sample sizes.
problem The cold posterior effect in approximate Bayesian inference for small datasets.
method Investigation through PAC-Bayes generalization bounds, focusing on temperature parameter λ.
result The temperature parameter λ in PAC-Bayes bounds captures the cold posterior effect.
This work introduces a method for visualizing high-dimensional posteriors using hierarchical tree-valued predictions.
problem Visualizing high-dimensional posterior distributions for complex problems like image restoration.
method A neural network predicts a tree-valued hierarchical summarization of the posterior distribution in a single forward pass.
result The method efficiently summarizes and visualizes posteriors, achieving comparable results to hierarchical clustering but at a much faster speed.
Bayesian bandits use double sampling to balance exploration and exploitation.
problem Balancing exploration and exploitation in real-world systems.
method Develops a double sampling technique to balance exploration and exploitation in Bayesian settings.
result Empirically shows reduced cumulative regret compared to state-of-the-art alternatives.
This technical note presents a new approach to carrying out the kind of exploration achieved by Thompson sampling, but without explicitly maintaining or sampling from posterior distributions. The approach is based on a bootstrap technique that uses a combination of observed and artificially generated data. The latter s…
Graph Posterior Network improves uncertainty estimation for node classification in interdependent graphs.
problem Uncertainty quantification for non-independent node-level predictions in graphs.
method Derives axioms for expected predictive uncertainty, proposes Graph Posterior Network (GPN) which performs Bayesian posterior updates.
result GPN outperforms existing approaches for uncertainty estimation in semi-supervised node classification.
The paper explores efficient posterior approximation methods in variational inference.
problem Efficient model optimization with little emphasis on the choice of approximating posterior.
method Develops a rich family of approximating posteriors using transformations on distributions.
result A particular method employing transformations on distributions yields better posterior distributions.
This work explores how overparametrization and priors affect Bayesian neural network posteriors.
problem Symmetries, non-identifiabilities, and weight-space priors fragment and inflate BNN posteriors.
method We study the interplay between overparametrization and priors in BNN posteriors, deriving key phenomena and validating through experiments.
result Overparametrization induces structured, prior-aligned weight posterior distributions.
This work uses model uncertainty for efficient exploration in sparse reward environments.
problem Challenging exploration in sparse reward reinforcement learning environments.
method Implicit generative modeling approach to estimate Bayesian uncertainty of the agent's belief of the environment dynamics.
result Our implicit generative model consistently outperforms competing approaches in data efficiency for exploration.
A new exploration method for bandit and reinforcement learning.
problem Uncertainty quantification in exploration.
method Residual Overfit Method of Exploration (ROME).
result ROME drives exploration towards actions with overfitting.
FP-BMA improves generalization by encouraging flat posteriors in Bayesian Model Averaging.
problem Lack of flat posterior in approximate Bayesian inference methods hinders effective Bayesian Model Averaging.
method Proposes Flat Posterior-aware Bayesian Model Averaging (FP-BMA) and Flat Posterior-aware Bayesian Transfer Learning schemes.
result FP-BMA successfully captures flat posteriors, improving generalization performance.
Proposes an amortized variational framework for Deep Q Networks.
problem Efficient exploration in deep reinforcement learning.
method Amortized variational inference for action value function approximation.
result Significantly less learning parameters and better performance.
Enhances SMC² with Hessian info for more efficient posterior approximation.
problem Improving accuracy and efficiency in Bayesian inference.
method Integrates second-order information (Hessian) into SMC²'s proposal distribution.
result Second-order proposals lead to more accurate posterior approximations and better step-size selection.
New method quantifies uncertainty in reinforcement learning models.
problem Quantifying uncertainty over expected cumulative rewards in reinforcement learning.
method Proposes a new uncertainty Bellman equation to more accurately estimate value function variance.
result Our method converges to the true posterior variance over values and improves sample-efficiency.
Study improves fractional posterior for 1-bit matrix completion.
problem Estimating a binary matrix from observed entries.
method Fractional posterior approach with low-rank factorization and spectral scaled Student priors.
result Concentration results for fractional posterior, demonstrating effectiveness in matrix recovery.
BDQN uses Bayesian deep Q-networks for efficient exploration in high-dimensional RL.
problem Efficient exploration in high-dimensional reinforcement learning environments.
method Bayesian deep Q-networks with Thompson sampling for efficient exploration and exploitation.
result BDQN achieves higher returns faster than DDQN through efficient exploration and exploitation.
Machine learning techniques improve Bayesian computation for complex data.
problem Infeasible posterior computation in high-dimensional models.
method Improving posterior computation using machine learning techniques.
result Potential to enhance Bayesian computation efficiency.
Transformer learns to infer partial MDPs for efficient in-context adaptation and exploration.
problem Efficiently adapt and explore in-context without gradient-based updates.
method Uses a transformer to learn inference from training tasks, considering hypothesis space of partial models.
result Adaptation speed and exploration-exploitation balance approach those of an exact posterior sampling oracle.
New method recovers clean data from corrupted samples.
problem Recovering clean data from corrupted samples with uncertainty.
method Probabilistic Tomographic Auto-Encoder method that derives reduced entropy condition approximate inference.
result Superior performance in imputation and de-noising compared to existing methods.
cKAM improves adaptive sampling by incorporating a cyclical stepsize scheme.
problem Adaptive Metropolis algorithms can get stuck in local modes.
method cKAM uses a cyclical stepsize scheme to encourage exploration and escape from local modes.
result cKAM successfully escapes local modes and converges to the true posterior distribution.
New MCMC method for complex models with large variables.
problem Inference on posterior model probabilities in large model spaces.
method Reversible genetically modified mode jumping Markov chain Monte Carlo (GMJMCMC).
result Introduced a proper MCMC with correct limiting distribution.
Paper uses RL and diffusion models to solve Bayesian inverse problems.
problem Bayesian inverse problems with latent biases.
method Relative Trajectory Balance (RTB) for RL, conditional diffusion models, off-policy backtracking exploration.
result RTB improves diffusion model posteriors for inverse problems.
Inference Trees adaptively sample to balance exploration and exploitation.
problem Balancing exploration and exploitation in adaptive inference methods.
method Inference Trees use hierarchical partitions and online learning to adaptively sample.
result ITs identify high posterior mass regions and maintain uncertainty estimates.
Bayesian neural networks struggle with accuracy and uncertainty quantification in complex models.
problem Challenges in achieving high predictive performance and reliable uncertainty estimates in Bayesian neural networks.
method Investigates computational costs, accuracy, and uncertainty quantification in Bayesian neural networks with different inference techniques.
result Variational inference provides better uncertainty quantification than Markov chain Monte Carlo, and stacking/ensembling variational approximations can achieve similar accuracy at reduced cost.
Develops Cyclical SG-MCMC for exploring multimodal posterior distributions in deep learning.
problem High-dimensional, multimodal posterior distributions in Bayesian deep learning.
method Cyclical stepsize schedule in SG-MCMC to discover and characterize modes.
result Non-asymptotic convergence of the proposed algorithm.
Most provably-efficient learning algorithms introduce optimism about poorly-understood states and actions to encourage exploration. We study an alternative approach for efficient exploration, posterior sampling for reinforcement learning (PSRL). This algorithm proceeds in repeated episodes of known duration. At the sta…
Bayesian neural networks explore rare fluctuations for better feature learning.
problem Understanding rare but dominant fluctuations in Bayesian neural networks.
method Large-deviation theory and joint optimization over predictors and internal kernels.
result Posterior rate function optimization reveals data-dependent kernel selection.
New priors improve Bayesian neural networks without cooling.
problem Bayesian neural networks underfit on clean datasets.
method Introduce DirClip and confidence priors to replace cooling.
result DirClip and confidence priors outperform cold posterior.
Improves Bayesian inference for deep models to better approximate posterior distributions.
problem Bayesian deep learning struggles with intractable posterior distributions, leading to overconfident predictions.
method Uses variational inference to approximate posterior distributions, proposing a unified view and improving inference for deep Gaussian processes.
result Variational inference can provide a lower bound for marginal likelihood, facilitating model selection and optimization.
Efficiently samples posterior distributions using Langevin dynamics.
problem Challenges in generating diverse posterior samples in high-dimensional spaces.
method Simulates Langevin dynamics in the noise space of a pre-trained generative model.
result Noise-space Langevin dynamics approximates the posterior without restarting the full sampling chain.
New approach uses autoregressive models to explore and quantify uncertainty in decision-making.
problem Quantifying and exploring uncertainty in online decision-making.
method Reformulates uncertainty as missing future outcomes, training autoregressive models for next-outcome prediction.
result Establishes a reduction from online learning to offline next-outcome prediction, controlling Bayesian regret by sequence prediction loss.
ICSGLD improves efficiency in posterior sampling for big data.
problem Efficient posterior sampling for large datasets.
method Embarrassingly parallel multiple-chain CSGLD with efficient interactions.
result ICSGLD is more efficient than a single-chain CSGLD.
Score-based martingale posteriors improve uncertainty quantification in deep neural networks.
problem Uncertainty quantification in deep neural networks
method Score-based martingale posteriors
result SMPs provide a fast, deterministic way to simulate the limiting random variable.
Proposes EVE for efficient exploration in reinforcement learning.
problem Efficient exploration in reinforcement learning.
method EVE: a recipe for posterior over parameters, facilitating efficient exploration.
result Competitive performance on benchmarks, efficient exploration confirmed.
Improved variational inference using HMC steps.
problem Improving posterior approximation beyond parametric families.
method Incorporating Hamiltonian Monte Carlo steps into variational lower bound.
result Asymptotic convergence to the true posterior with HMC steps.
A student-like approach to reinforcement learning by practicing before evaluating.
problem Minimizing cumulative regret in reinforcement learning with an initial practice phase.
method Posterior Sampling for Pure Exploration (PSPE) and Posterior Sampling for Reinforcement Learning (PSRL).
result The combination of PSPE and PSRL achieves optimal simple regret and cumulative regret.
A new method uses MCMC-assisted normalizing flows for efficient Bayesian sampling.
problem Sampling from complex posterior distributions in Bayesian statistics.
method Training a normalizing flow using direct KL divergence and MCMC assistance.
result The method improves sampling efficiency for complicated posterior distributions.
New Thompson sampling uses local uncertainty for better decision making.
problem Sequential decision making with exploration-exploitation dilemma.
method Proposes a new probabilistic modeling framework using local latent variable uncertainty for Thompson sampling, with variational inference and semi-implicit structure.
result Thompson sampling guided by local uncertainty achieves state-of-the-art performance with low computational complexity.
Kolmogorov-Arnold network improves GW catalog posterior construction.
problem Efficiently constructing posterior distributions for GW catalogs.
method Using the Kolmogorov-Arnold network to create lightweight neural density estimators.
result Kolmogorov-Arnold network achieves superior interpretability and accuracy in posterior construction.
Randomized exploration in linear bandits achieves optimal regret bounds.
problem Optimizing exploration in high-dimensional linear bandit problems.
method Analysis of Thompson sampling without forced optimism.
result Randomized exploration algorithms achieve an O ( d n log ( n ) ) O(d\sqrt{n} \log(n)) O ( d n log ( n )) regret bound in smooth, strongly convex action spaces.