This paper advances sample-efficient learning for partially observable RL by introducing B-stability and new algorithms.
problem Hard sample complexity for learning near-optimal policies in partially observable RL.
method Proposes B-stability as a unified structural condition and develops new algorithms for sample-efficient learning.
result Any B-stable PSR can be learned with polynomial samples, improving over current best complexities.
New Thompson Sampling for partially observed context bandits reduces regret logarithmically with time.
problem Improving Thompson Sampling for partially observed context bandits.
method Proposed a Thompson Sampling algorithm for partially observable contextual multi-armed bandits with theoretical performance guarantees.
result Regret scales logarithmically with time and the number of arms, and linearly with the dimension.
The paper cleans label noise in supervised classification using Bernoulli sampling.
problem Label noise degrades supervised classifier performance.
method Proposes a label noise cleaning method based on Bernoulli random sampling.
result The method separates clean and noisy observations without prior label information.
Paper proposes learning system dynamics from irregularly-sampled partial observations.
problem Capturing dynamics of multi-agent systems with irregular and partial observations.
method LG-ODE, a latent ordinary differential equation model using graph neural networks and neuralODE.
result Demonstrates effectiveness on motion capture, spring system, and charged particle datasets.
This paper addresses the problem of filtering with a state-space model. Standard approaches for filtering assume that a probabilistic model for observations (i.e. the observation model) is given explicitly or at least parametrically. We consider a setting where this assumption is not satisfied; we assume that the knowl…
Validates policies using past observational data with guarantees about out-of-sample performance.
problem Evaluating decision policies using past data observed under a different policy.
method Sample-splitting method to draw inferences about the entire loss distribution with finite-sample coverage guarantees.
result Valid inferences about out-of-sample loss with finite-sample coverage guarantees, accounting for model misspecifications.
Enhanced feedback model improves sample-efficiency in POMDPs.
problem Exponential hardness of learning in POMDPs.
method Multiple observations in hindsight feedback model.
result Sample-efficient learning possible for new subclasses of POMDPs.
Efficiently estimates causal effects from observational data.
problem Estimating the effect of atomic interventions using observational samples.
method Quantitative analysis of causal graphs, algorithm with sample and time complexity.
result Algorithm that estimates causal effects with high probability and low TV distance.
The paper develops algorithms for competitive RL in partially observable MGs.
problem Challenges in reinforcement learning with function approximation and partial observability.
method Proposes posterior sampling methods for self-play and adversarial learning in zero-sum MGs.
result Developed algorithms achieve low regret bounds scaling sublinearly with GEC and episode number.
Combines observational and randomized data to estimate treatment effects.
problem Estimating heterogeneous treatment effects using only observational data is biased.
method Two-step framework: learn shared structure from observational data, then data-specific structures from randomized data.
result Combining observational and randomized data improves treatment effect estimation.
New algorithm learns Bayesian network structures with fewer samples.
problem Learning Bayesian network structures with limited observational data.
method Active sampling strategy to select variables for observation.
result Active algorithm finds structures close to optimal with fewer samples.
iTimER learns from reconstruction errors to represent irregularly sampled time series.
problem Learning from irregularly sampled time series with missing data.
method iTimER models reconstruction errors as a proxy for unobserved values, using a mixup strategy and a Wasserstein metric.
result iTimER outperforms state-of-the-art methods in classification, interpolation, and forecasting tasks.
New method recovers matrix column space with active sampling for better results.
problem Recovering column space of partially observed matrices with limited data.
method Alternating minimization with active sampling strategy.
result Active sampling improves convergence to true column space with higher probability.
The paper tackles imbalance in production data by proposing sampling methods to improve model performance on underrepresented observations.
problem Imbalance in production data negatively impacts model predictive performance on underrepresented observations.
method Three sampling approaches are investigated to adjust for imbalance in training data and improve model performance.
result Fitting a model using sampled data yields a small reduction in overall predictive performance but a better performance on underrepresented observations.
New method uncovers zero entropy in dependent observations after finite samples.
problem Understanding uncertainty reduction in dependent observations.
method Minimum list entropy coupling, greedy algorithm.
result Zero entropy achieved with O(log(1/P_min)) samples for dependent observations.
Study efficient reinforcement learning for partially observed systems with linear structure.
problem Efficient reinforcement learning for partially observed Markov decision processes with linear structure.
method Proposes OP-TENET algorithm using a Bellman operator with finite memory, adversarial integral equation, and optimistic exploration.
result Achieves ε-optimal policy within O(1/ε^2) episodes with polynomial sample complexity in intrinsic dimension.
New algorithms learn POMDPs efficiently with hindsight observability.
problem Hardness of learning in POMDPs due to partial observability.
method Hindsight Observable Markov Decision Process (HOMDP) and new algorithms for tabular and function approximation settings.
result Sample-efficient learning in POMDPs with optimal dependence on latent state and observation cardinalities.
Formalizes identifying information to answer key questions about machine learning from uncertain and novel observations.
problem Understanding and quantifying information from uncertain and novel observations in machine learning.
method Formalizes identifying information, defines hypothesis identification and sample complexity, and proves sample complexity properties for various data-generating processes.
result Proves the information theoretic characteristics of hypothesis identification and sample complexity, and shows how to compute identifying information and novel information.
Matrix completion is a classical problem in data science wherein one attempts to reconstruct a low-rank matrix while only observing some subset of the entries. Previous authors have phrased this problem as a nuclear norm minimization problem. Almost all previous work assumes no explicit structure of the matrix and uses…
This paper tackles sample-efficient reinforcement learning for partially observable Markov games.
problem Learning in partially observable Markov games with incomplete information.
method A simple algorithm combining optimism and Maximum Likelihood Estimation (MLE) for self-play, and a variant of optimistic MLE for adversarial opponents.
result The proposed algorithms achieve approximate Nash, correlated, and coarse correlated equilibria in polynomial samples for weakly revealing POMGs.
Partially observable Markov decision processes (POMDPs) with continuous state and observation spaces have powerful flexibility for representing real-world decision and control problems but are notoriously difficult to solve. Recent online sampling-based algorithms that use observation likelihood weighting have shown un…
RichID learns optimal control policies from nonlinear observations.
problem Continuous control with unknown nonlinearity in system model.
method RichID algorithm using a least-squares regression oracle.
result First provable sample complexity guarantee for continuous control.
New algorithm proves RL from partial obs is feasible.
problem Difficulty in learning from partial observability.
method Optimism combined with MLE for weakly revealing POMDPs.
result Simple algorithm guarantees polynomial sample efficiency.
In this paper, we consider matrix completion from non-uniformly sampled entries including fully observed and partially observed columns. Specifically, we assume that a small number of columns are randomly selected and fully observed, and each remaining column is partially observed with uniform sampling. To recover the …
Modern CATE models often fail to outperform a trivial zero-effect predictor, highlighting significant challenges.
problem Lack of robustness in CATE models when applied to real-world data.
method Large-scale benchmark study using diverse observational sampling strategies and novel statistics.
result 62% of CATE estimates have higher MSE than a trivial zero-effect predictor, indicating poor performance.
We study covariance matrix estimation for the case of partially observed random vectors, where different samples contain different subsets of vector coordinates. Each observation is the product of the variable of interest with a 0−1 Bernoulli random variable. We analyze an unbiased covariance estimator under this mod…
DAISI improves data assimilation for complex systems with noisy observations.
problem Limited accuracy of classical DA methods in complex, nonlinear systems.
method Generative models with inverse sampling for flexible probabilistic inference.
result DAISI achieves accurate filtering results in challenging nonlinear systems.
DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
problem Efficiently discovering targets in partially observable environments with limited sampling.
method DiffATD uses diffusion dynamics to maintain a belief distribution over unobserved states, balancing exploration and exploitation.
result DiffATD outperforms baselines and supervised methods in diverse domains.
DWTS uses observational data to improve clinical trial efficiency.
problem Lack of definitive conclusions from randomized clinical trials due to insufficient patient cohorts and confounding biases.
method DWTS combines observational data with randomized clinical trials using Doubly Debiased LASSO (DDL) to identify reliable covariates.
result DWTS reduces cumulative regret in clinical trials compared to standard methods.
Study efficient graph optimization with noisy data.
problem Optimizing functions on graphs with noisy observations.
method Best-arm identification and simulated annealing variants.
result Near-optimal solutions found with small query numbers.
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
Thompson Sampling improves decision-making in partially observed contexts.
problem Balancing exploration and exploitation in partially observed contextual bandits.
method Thompson Sampling policy for learning optimal arms from noisy linear functions of unobserved context vectors.
result Thompson Sampling achieves poly-logarithmic regret and square-root consistency of parameter estimation.
This paper improves system identification by reducing sample complexity for high-dimensional linear dynamical systems.
problem High sample complexity for learning partially observed linear dynamical systems in high dimensions.
method Introduces an ℓ1-regularized estimation method that reduces sample complexity from linear to logarithmic with system dimension. result Markov parameters can be learned with logarithmic number of samples relative to system dimension, improving sample complexity.
Study evaluates ML methods for two-sample testing with right-censored data.
problem Evaluating ML methods for two-sample testing with right-censored data.
method Developed and compared several ML-based methods with classical tests.
result Proposed methods outperform classical tests in terms of statistical power.
The paper develops methods to estimate treatment effects in sample selection models.
problem Evaluation of treatments when outcomes are only observed for a subpopulation due to sample selection or attrition.
method Combines selection-on-observables and instrumental variable assumptions with double machine learning for treatment evaluation.
result Proposed estimators are asymptotically normal and root-n consistent.
A new method combines scores of individual observations to efficiently approximate posterior distributions.
problem Handling posterior distributions conditioned on multiple observations with neural methods.
method Conditional score modeling to combine learned scores from individual observations.
result Sample-efficient method that can aggregate multiple observations at inference time.
Estimates proportions of LLM-generated text in mixed documents.
problem Estimating the proportion of text generated by a pre-specified LLM in mixed documents.
method Developed estimators for two observation regimes: full observation and pivotal reduction, and established sample complexity bounds.
result Full observation estimators require fewer samples than pivotal reduction estimators.
Established recurrent neural networks are well-suited to solve a wide variety of prediction tasks involving discrete sequences. However, they do not perform as well in the task of dynamical system identification, when dealing with observations from continuous variables that are unevenly sampled in time, for example due…
kNNSampler imputes missing values from their distributions using kNN.
problem Impute missing values from their distributions.
method Randomly samples from the observed responses of the k most similar units.
result Estimates the conditional distribution of missing values.
Study on estimating Gumbel--Max watermark proportions in edited documents.
problem Estimating the proportion of a document generated from a watermarked LLM.
method Comparison of full observation and pivotal reduction observation regimes; development of estimators and information-theoretic lower bounds.
result Full observation yields a substantially smaller sample complexity compared to pivotal reduction.
Adaptive sampler improves recommendation for implicit feedback data.
problem Challenges in predicting user preferences from implicit feedback data.
method Noisy-label robust learning for adaptive sampler design.
result Significant improvement in recommendation quality on real-world datasets.
Study on estimating causal effects with limited data and multiple environments.
problem Estimating causal effects under hidden confounding with unpaired data and sparse effects.
method Instrumental variable (IV) regression with cross-fold sample splitting and ℓ1-regularized estimation. result Proposed GMM-type estimator is consistent as the number of environments grows.
Study integrates machine learning with SAA for optimizing decisions based on uncertain parameters and covariates.
problem Optimizing decisions under uncertain parameters and covariates.
method Data-driven frameworks integrating machine learning prediction models within SAA for scenario generation.
result Consistent and asymptotically optimal solutions under certain conditions, with finite sample guarantees.
Proposes LDIDPs for efficient sequential data generation from latent dynamical models.
problem Challenges in generating high-fidelity sequential samples from latent dynamical models.
method Utilizes implicit diffusion processes to sample from latent dynamical processes.
result Demonstrates accurate learning of dynamics and efficient generation of high-quality sequential data.
New method approximates POMDPs with PB-MDPs, providing error bounds and practical algorithms.
problem Difficulty in solving POMDPs with continuous or hybrid state and observation spaces.
method Bounding particle filtering error and adapting MDP algorithms to POMDPs.
result General theory and practical algorithms for POMDPs with no direct dependence on state and observation space sizes.
This paper studies the problem of {\em learning} the probability distribution PX of a discrete random variable X using indirect and sequential samples. At each time step, we choose one of the possible K functions, g1,…,gK and observe the corresponding sample gi(X). The goal is to estimate the proba…
ETC learns minimal representations for reinforcement learning in POMDPs.
problem Sample complexity challenges in reinforcement learning for POMDPs.
method ETC learns low-dimensional features and embeddings at two levels, optimizing policy.
result ETC achieves polynomial sample complexity for POMDPs with low-rank transition kernels.
A new sampling method balances multi-label datasets by preserving category frequency order.
problem Sampling challenges in multi-label datasets with varying label frequencies.
method Uses multivariate Bernoulli distribution and label dependencies to estimate and weight label combinations.
result Produces a more balanced sub-sample with enhanced representation of minority categories.