Algorithm finds latent structure in value functions for improved reinforcement learning.
problem Finding latent structure in value functions for efficient reinforcement learning.
method Proposes a practical algorithm using two posterior distributions over state abstractions and abstract-state values.
result Substantial performance gains in multi-task settings where tasks share a common, low-dimensional representation.
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.
This work extends HiP-MDPs to robust state abstractions for multi-task and meta-reinforcement learning.
problem Limited observability of state in HiP-MDPs for real-world scenarios with rich observation spaces.
method Inspired by Block MDPs, the work extends HiP-MDPs to enable robust state abstractions for multi-task and meta-reinforcement learning.
result Transfer and generalization bounds based on task and state similarity, and sample complexity bounds that depend on the aggregate number of samples across tasks.
The paper introduces a method to learn Markov state abstractions for reinforcement learning.
problem Learning Markov state representations in complex environments.
method The paper introduces a novel set of conditions and a training procedure combining inverse model estimation and temporal contrastive learning.
result The approach learns representations that capture the underlying structure of the domain and improve sample efficiency.
We present an algorithm, HOMER, for exploration and reinforcement learning in rich observation environments that are summarizable by an unknown latent state space. The algorithm interleaves representation learning to identify a new notion of kinematic state abstraction with strategic exploration to reach new states usi…
Proposes method to learn state abstractions that generalize across environments.
problem Learning abstractions that generalize in block MDPs.
method Invariant causal prediction to learn model-irrelevant state abstractions (MISA).
result Proves high probability of outputting a state abstraction corresponding to causal feature set for return.
This work defines a complexity measure for BAMDP planning and introduces state abstraction for more efficient approximate planning.
problem The computational intractability of exact BAMDP planning solutions.
method Define a complexity measure for BAMDP planning, introduce state abstraction, and develop an approximate planning algorithm.
result Introduces a computationally tractable approximate planning algorithm using state abstraction.
Deep neural network learns discrete state abstractions for efficient planning.
problem Efficient sequential decision making in large state spaces.
method Information bottleneck method for learning approximate bisimulations using deep neural encoders and action-conditioned HMM.
result Trained method efficiently plans for unseen goals in multi-goal reinforcement learning.
STAR framework reduces OPE variance by distilling complex problems into discrete ARPs.
problem High variance and bias in off-policy evaluation methods.
method STAR framework that includes various OPE estimators and leverages state abstraction.
result Predictions from ARPs estimated from off-policy data are asymptotically correct.
Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be…
A new method shapes reinforcement learning environments by abstracting large state spaces.
problem Learning in large, noisy environments with sparse feedback.
method Environment shaping using state abstraction.
result Agent's policy in shaped environment preserves near-optimal behavior in original environment.
In this semi-tutorial paper, we first review the information-theoretic approach to account for the computational costs incurred during the search for optimal actions in a sequential decision-making problem. The traditional (MDP) framework ignores computational limitations while searching for optimal policies, essential…
Differential privacy of Gaussian process posterior sampling
problem Privacy of posterior sample paths from Gaussian process
method Intrinsic randomness yields DP guarantees
result Intrinsic randomness yields DP guarantees
Proposes sampling from reverse diffusion posteriors for contextual bandits.
problem Complex distributions in contextual bandits.
method Approximate posterior sampling with a diffusion model prior using Laplace approximation.
result Empirically consistent and efficient approximations for contextual bandits.
Method estimates Bayesian evidence from posterior samples using normalizing flows.
problem Estimating Bayesian evidence from posterior samples.
method Normalizing flows for evidence estimation.
result Method is more robust to sharp features in posterior distributions, especially in higher dimensions.
A new method for sampling complex posterior distributions in DDMs.
problem Challenging posterior distributions in DDMs.
method Divide-and-Conquer Posterior Sampling (DCPS)
result Significantly reduces approximation error without retraining.
New method samples from posterior distributions efficiently.
problem Posterior sampling in score-based models is intractable.
method Annealed Langevin Monte Carlo with KL and Fisher divergence.
result Tractable sampling from distributions close to posterior and prior.
Increasingly complex datasets pose a number of challenges for Bayesian inference. Conventional posterior sampling based on Markov chain Monte Carlo can be too computationally intensive, is serial in nature and mixes poorly between posterior modes. Further, all models are misspecified, which brings into question the val…
This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction. Specifically, we combine state aggregation with the options framework and demonstrate that they work well together and indeed it is only after one combines the two that the full benefit of each is re…
Flow Annealing Posterior Sampling unifies stochastic-process regression and PDE inverse problems.
problem Function-space posterior sampling for stochastic processes and inverse problems.
method Flow Annealing Posterior Sampling (FAPS) using pretrained function-space flow-matching priors.
result Coherent posterior samples with accurate uncertainty quantification.
LMC-TS uses MCMC for efficient posterior sampling in contextual bandits.
problem Efficiency of Thompson sampling for high-dimensional contextual bandits.
method Langevin Monte Carlo for direct posterior sampling.
result LMC-TS achieves sublinear regret bound for linear contextual bandits.
Unified framework for model-based RL with sample complexity guarantees.
problem Designing efficient posterior sampling methods for model-based RL.
method Optimistic posterior sampling, Hellinger distance reduction, data likelihood measurement.
result Unified algorithms with state-of-the-art sample complexity guarantees.
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.
Improved sampling for high-dimensional posteriors with underdamped Langevin.
problem Scalability issues in high-dimensional problems with approximate Thompson sampling.
method Underdamped Langevin Monte Carlo for accelerated posterior concentration.
result Logarithmic regret improvement from i l d e O ( d ) \mathcal{ ilde O}(d) i l d e O ( d ) to i l d e O ( d ) \mathcal{ ilde O}(\sqrt{d}) i l d e O ( d ) . New method improves posterior sampling for complex data models.
problem Sampling from posterior distributions in high-dimensional data.
method Tilted transport technique combining denoising oracle and log-likelihood.
result Boosted posterior is strongly log-concave, facilitating easier sampling.
Posterior sampling from diffusion models is computationally hard.
problem Sampling from posterior distributions in diffusion models is intractable.
method Analyzes the computational complexity of posterior sampling in diffusion models.
result Posterior sampling is computationally intractable under cryptographic assumptions.
A novel diffusion method for Bayesian posterior sampling with theoretical guarantees.
problem Efficiently sampling from complex posterior distributions in Bayesian inversion.
method Diffusion-based posterior sampling using Langevin dynamics and PnP framework.
result The method converges even for multi-modal posterior distributions with theoretical error bounds.
Combining diffusion models with Langevin dynamics improves posterior sampling efficiency.
problem Sampling from noisy posterior distributions efficiently.
method Annealed Langevin dynamics combined with diffusion models.
result Achieves posterior sampling in polynomial time with a weaker score error bound.
New method improves sample-efficiency in neural posterior estimation using simulator gradients.
problem High-fidelity posterior estimation with complex physical simulations is time-consuming.
method Neural Posterior Estimation (NPE) with differentiable simulators and gradient information.
result Improves sample-efficiency in posterior density estimation.
New method optimizes Bayesian optimization for high-dimensional posterior samples.
problem Difficult inner-loop optimization of posterior sample paths in Bayesian optimization.
method Global rootfinding approach with carefully selected starting points.
result The method discovers the global optimum most of the time with just one starting point per set.
Develops a new method for sampling from Bayesian credible sets using deep generative quantile learning.
problem Sampling from posterior distributions in high-dimensional spaces with intractable likelihoods.
method Uses deep neural networks to implicitly sample from Bayesian credible sets via a push-forward mapping and Monge-Kantorovich depth.
result Demonstrates improved performance and theoretical consistency of the quantile learning framework.
Diffusion models tackle noisy inverse problems with posterior sampling.
problem Efficiently solving general noisy inverse problems.
method Approximation of posterior sampling for diffusion models.
result Diffusion models can handle various noise statistics and nonlinear problems.
Posterior refinement improves sample efficiency in Bayesian neural networks.
problem Bayesian neural networks suffer from poor predictive performance due to inaccurate posterior approximations.
method Propose refining Gaussian approximate posteriors with normalizing flows to improve predictive distributions.
result Posterior refinement yields competitive predictive performance with minimal computational overhead.
Proposes a method to sample from flat basins of posterior distributions in Bayesian deep learning.
problem Sampling from multi-modal posterior distributions leads to overfitting due to trapping in bad modes.
method Introduces an auxiliary guiding variable to bias MCMC sampling towards flat basins of the energy landscape.
result The method converges faster and outperforms existing methods in sampling from flat basins of the posterior.
The paper proposes a Gibbs sampler for neural network posterior sampling.
problem Sampling from the posterior of neural networks.
method Adding noise to activations and using a Gibbs sampler.
result The Gibbs sampler achieves similar performance to MCMC methods on real and synthetic data.
New method efficiently samples Gaussian process posteriors without cubic scaling.
problem Intractable posterior distributions in Gaussian processes.
method Decomposes Gaussian processes into prior and data components for scalable sampling.
result Fast posterior sampling at a fraction of the usual cost.
We prove exact BNN posterior convergence to GP limit and provide sampling methods.
problem Theoretical and empirical challenges in obtaining exact posterior distributions of wide BNNs.
method Theoretical proof and rejection sampling for generating exact samples.
result Exact BNN posterior converges to GP limit as width increases.
Posterior sampling-based EI achieves sublinear regret bounds for expensive function optimization.
problem Theoretical analysis of expected improvement (EI) in Bayesian optimization.
method Randomized posterior sampling of EI.
result Achieves sublinear Bayesian cumulative regret bounds.
PPT optimizes transformer behavior by steering its latent posterior using prior samples.
problem Eliciting desired behavior from transformers without backpropagation.
method Posterior Prefix Tuning (PPT) uses predictive Monte Carlo (PMC) samples and importance sampling to optimize the latent posterior.
result PPT optimizes transformer behavior without backpropagation, achieving high utility across different utility functions.
A new algorithm improves posterior sampling for linear inverse problems.
problem Efficiently sampling from posterior distributions in noisy linear inverse problems.
method Proposes \pddim, a DDIM-type sampler that separately samples along singular directions of the measurement operator.
result The method converges to the Bayesian posterior conditioned on the measurements.
Posterior sampling estimator achieves near-optimal recovery guarantees for signals from any prior distribution.
problem Characterizing measurement complexity for signals from any prior distribution, including the entire space.
method Characterization of measurement complexity using posterior sampling estimator for Gaussian measurements and any prior distribution.
result Posterior sampling estimator achieves near-optimal recovery guarantees for signals from any prior distribution, robust to model mismatch.
Learning latent variable models with stochastic variational inference is challenging when the approximate posterior is far from the true posterior, due to high variance in the gradient estimates. We propose a novel rejection sampling step that discards samples from the variational posterior which are assigned low likel…
Sampling from posterior distributions using Markov chain Monte Carlo (MCMC) methods can require an exhaustive number of iterations, particularly when the posterior is multi-modal as the MCMC sampler can become trapped in a local mode for a large number of iterations. In this paper, we introduce the pseudo-extended MCMC…
Meta-learning improves Bayesian causal discovery by sampling from the posterior.
problem Difficulty in estimating the full posterior over causal structures due to large number of possible graphs and functional relationships.
method Proposes a Bayesian meta-learning model that encodes key properties of the posterior and allows for sampling causal structures.
result Meta-Bayesian causal discovery allows for reliable sampling from the posterior over causal structures.
New methods for tuning alpha in Gibbs posteriors improve speed and accuracy.
problem Inconsistency in Bayesian inference and lack of fast tuning methods for alpha.
method Proposed two data-driven methods: sample-splitting and bootstrapping. Formulated alpha-posteriors for three models.
result Sample-splitting outperforms SafeBayes in speed and accuracy, especially in complex models.
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.
Improved predictive posterior density estimation through optimized importance sampling.
problem Low signal-to-noise ratio in posterior predictive densities.
method Optimized importance sampling using a test-time variational proxy.
result Significantly improved estimates of predictive posterior densities.
Bayesian inference for inverse problems using mean-shift interacting particles
problem Bayesian inference for inverse problems
method Amortized mean-shift interacting particles
result Improves accuracy of Bayesian inference by reducing the number of samples needed