New bounds show limitations of sample-wise information-theoretic generalization.
problem Limitations of sample-wise information-theoretic generalization bounds.
method Analysis of existing bounds and derivation of new bounds.
result No sample-wise information-theoretic bounds exist for expected squared generalization gap.
Study improves sampling from non-log-concave distributions using Fisher information.
problem Sampling from non-log-concave distributions with high Fisher information guarantees.
method Proximal sampler with RGO implementation, leveraging log-concave sampling results.
result Improved complexity guarantee in relative Fisher information for non-log-concave sampling.
New method corrects ML for informative sampling in time-series treatment outcomes.
problem Informative sampling in irregularly observed data hinders accurate treatment outcome forecasting.
method Formalized as covariate shift, proposed inverse intensity-weighting framework, TESAR-CDE.
result TESAR-CDE effectively learns treatment outcomes under informative sampling.
Estimates how much samples inform neural network training and function.
problem Measuring informativeness of samples in neural networks.
method Linearized network approximations for efficient computation.
result Efficient approximations show good accuracy for real-world models.
This paper improves sample efficiency in noisy inductive matrix completion with side-information.
problem Improving sample efficiency in noisy inductive matrix completion with side-information.
method Nonconvex projected gradient descent algorithm with spectral initialization.
result Achieves linear convergence and stable recovery at a sample complexity governed by the effective side-information dimension.
Improved bounds on learning algorithms' performance using conditional mutual information.
problem Bounding the generalization error of learning algorithms.
method Introducing conditional mutual information and disintegrated mutual information to tighten bounds.
result New bounds are tighter than previous ones, especially for noisy, iterative algorithms.
Estimates interactions between modalities for multimodal data.
problem Accurately quantifying interactions between different data types.
method Developed Lightweight Sample-wise Multimodal Interaction (LSMI) estimator using pointwise information theory.
result LSMI reveals fine-grained dynamics in multimodal data.
Mirror descent linked to information ratio via Bayesian regret bounds.
problem Understanding stability in mirror descent and its relation to information ratio.
method Developed a connection between mirror descent and information ratio using Bayesian regret bounds.
result Mirror descent with suitable estimators and distributions achieves bounds similar to information-directed sampling.
IDS improves sparse linear bandits by balancing information and regret.
problem Sparse linear bandits in high-dimensional decision-making.
method Information-directed sampling (IDS) with Bayesian regret bounds and empirical Bayesian sparse posterior sampling.
result IDS nearly matches existing lower bounds and significantly reduces regret.
Tensor completion requires fewer samples with weak side information.
problem Tensor completion with limited samples and side information.
method Algorithm utilizing weak side information to reduce sample complexity.
result Consistent estimator with O ( n 1 + κ ) O(n^{1+κ}) O ( n 1 + κ ) samples for any small constant κ > 0 κ> 0 κ > 0 . Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains. However, task requester usually has a limited amount of budget, thus it is desirable to have a policy to wisely allocate the budget to achieve better quality. In this paper, we study the princi…
Adaptive sampling improves graph diffusion models by maintaining uniform information speed.
problem Standard diffusion models overlook non-homogeneous dynamics on complex manifolds.
method Information-geometric framework using Fisher-Rao metric and Drift Variation Score (DVS).
result DVS solver ensures uniform rate of distributional change, improving structural fidelity and efficiency.
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.
Thompson Sampling bounds for contextual bandits with sub-Gaussian rewards.
problem Improving the performance of Thompson Sampling in contextual bandits with sub-Gaussian rewards.
method Proved comprehensive bounds on Thompson Sampling expected cumulative regret based on mutual information and lifted information ratio for sub-Gaussian rewards.
result Explicit regret bounds for various contextual bandit scenarios.
In the information-based paradigm of inference, model selection is performed by selecting the candidate model with the best estimated predictive performance. The success of this approach depends on the accuracy of the estimate of the predictive complexity. In the large-sample-size limit of a regular model, the predicti…
Enhances physics-informed neural networks with adaptive sampling and weighting.
problem Challenges in training physics-informed neural networks on complex problems.
method Hybrid adaptive sampling and weighting method.
result Consistently improves prediction accuracy and training efficiency.
Improves FI-PINNs by combining re-sampling and subset simulation for better failure probability estimation.
problem Estimating failure probability in physics-informed neural networks (PINNs).
method Adaptive sampling with re-sampling and subset simulation, using cosine-annealing for uniform to adaptive transition.
result Significant improvement in estimating failure probability and generating new training points in the failure region.
Meta-learning bound uses conditional mutual information.
problem Bounding generalization performance in meta-learning.
method Extends CMI framework to meta-learning with a meta-supersample.
result Explicit bound involving two CMI terms.
The paper sets lower bounds for sampling non-log-concave distributions using Fisher information.
problem Understanding the complexity of sampling non-log-concave distributions.
method Proves two lower bounds using Fisher information in the context of sampling.
result Lower bounds on the complexity of sampling non-log-concave distributions, ruling out high-accuracy algorithms.
The paper proposes a method to detect and filter noisy or mislabeled data using pointwise mutual information.
problem Detecting and filtering noisy or mislabeled data in deep learning models.
method A mutual information-based framework quantifying statistical dependencies between inputs and labels.
result The method effectively filters low-quality samples, improving classification accuracy by up to 15%.
Ensemble sampling approximates Thompson sampling for complex models.
problem Computational intractability of exact posterior distributions.
method Thompson sampling approximation with information-theoretic concepts.
result Established a first rigorous regret bound for ensemble sampling.
Improved mean estimation for symmetric distributions with finite-sample guarantees.
problem Estimating the mean of a symmetric distribution from samples.
method Using Fisher information rate for finite-sample guarantees.
result Finite-sample convergence close to subgaussian with variance 1/(n * I_r), where I_r is r-smoothed Fisher information.
Optimizes stochastic linear bandits with efficient, asymptotically optimal algorithm.
problem Optimizing stochastic linear bandits with multiple actions.
method Frequentist information-directed sampling (IDS) with a surrogate for information gain.
result Asymptotically optimal and nearly worst-case optimal in finite time.
This work tackles online memory selection in continual learning using information theory.
problem Online selection of a representative replay memory from data streams.
method Information-theoretic criteria (surprise, learnability) and Bayesian model for efficient computation.
result InfoRS improves robustness against data imbalance compared to reservoir sampling.
The paper improves high-dimensional linear regression prediction and estimation using auxiliary samples.
problem Estimating and predicting high-dimensional linear regression models with auxiliary samples.
method Proposes Trans-Lasso for data-driven transfer learning, establishing optimality for prediction and estimation.
result Knowledge from auxiliary samples can improve learning performance in target problems.
Adaptive sampling improves deep learning efficiency by focusing on informative samples.
problem Expensive annotations and loss of sample informativeness in deep learning.
method Adaptive latent space sampling based on hardness-aware strategy.
result The proposed framework outperforms random sampling on various datasets.
RLFA estimates misstated monetary fraction with weighted sampling without replacement.
problem Estimating misstated monetary fraction with given accuracy and confidence.
method Developed new confidence sequences for weighted average of unknown values using randomized weighted sampling and side information.
result Adaptive methods improve accuracy of estimates based on side information's predictive power.
Efficiently learns Gaussian tree models with near-optimal sample complexity.
problem Learning tree-structured Gaussian distributions efficiently.
method Conditional mutual information tester for Gaussian variables, near-optimal sample complexity.
result Near-optimal sample complexity for structure learning of Gaussian tree models.
WiGS improves active learning for regression by dynamically selecting informative samples.
problem Reducing labeling costs in regression tasks.
method Formulated as a reinforcement learning problem, WiGS adapts the exploration-investigation balance.
result WiGS outperforms static methods in accuracy and labeling efficiency, especially in irregular data density.
The paper extends Thompson Sampling to infinite action spaces using information theory.
problem Addressing the limitation of finite action spaces in Thompson Sampling.
method Information-theoretic analysis, extending rate-distortion theory to infinite action spaces.
result Derives a near-optimal regret bound for bandits with infinite and continuous action spaces.
Study reveals mutual information is crucial for understanding algorithm performance in stochastic convex optimization.
problem Uncertainty in capturing the exceptional performance of learning algorithms using existing information-theoretic generalization bounds.
method Examined the relationship between mutual information and generalization in stochastic convex optimization.
result Mutual information is necessary for true risk minimization in stochastic convex optimization, indicating existing bounds fall short.
The paper analyzes how the one-dimensional Wasserstein distance captures pointwise density differences in finite samples.
problem Uncertainty in identifying density differences when supports overlap and densities have substantial pointwise differences.
method Analysis using the Poisson process and neural spike train decoding.
result The one-dimensional Wasserstein distance highlights meaningful density differences related to both rate and support.
The paper proves sampling methods using discrete-time processes and information theory.
problem Proving convergence guarantees for diffusion-based sampling methods.
method Directly works with discrete-time stochastic processes and uses information theory.
result Discrepancy between sampling and comparison processes is bounded using information theory.
The paper studies how quickly samples from Langevin dynamics become independent.
problem Understanding the dependence between samples along Langevin dynamics and related algorithms.
method Measures dependence via Φ Φ Φ -mutual information and proves strong data processing inequalities. result The Φ Φ Φ -mutual information between samples decreases exponentially to zero. Estimates expected information gain using density approximations and dimension reduction.
problem Estimating expected information gain in nonlinear and non-Gaussian settings.
method Flexible transport-based schemes for EIG estimation, optimal sample allocation, and gradient-based upper bounds on mutual information.
result Optimal sample allocation and dimension reduction schemes improve EIG estimation accuracy and convergence rate.
CuBAS selects informative data points based on curvature for better classification.
problem Lack of efficient sampling strategies for maximizing dataset informativeness.
method Information-geometric framework using curvature scores to select labeled data.
result Consistent and statistically significant improvements over random and uncertainty-based sampling.
Novel algorithms for multi-agent reinforcement learning reduce sample complexity.
problem Efficiently learning Nash equilibria in multi-agent settings.
method Information-Directed Sampling (IDS) principles applied to multi-agent reinforcement learning.
result Sample-efficient algorithms for learning Nash equilibria in various multi-agent settings.
New bounds improve generalization in learning scenarios.
problem Limitations of existing information-theoretic bounds in SCO problems.
method Sample-conditioned hypothesis stability and neighboring-hypothesis matrix.
result Sharper generalization guarantees in various learning scenarios.
Proposes a neural network method to combine nonprobability and probability survey samples.
problem Combining nonprobability and probability survey samples for accurate population mean estimation.
method Uses a deep neural network to estimate sampling scores from nonprobability samples and combines them with probability sample information.
result Proposed estimators improve robustness to parametric propensity-score misspecification, especially for nonlinear selection mechanisms.
MIRO learns robust latent spaces by maximizing mutual information with future information.
problem Robust perception in complex, unstructured environments with low sample complexity.
method MIRO maximizes mutual information in a latent space for model-based reinforcement learning.
result MIRO outperforms reconstruction objectives in cluttered scenes.
Active learning selects most informative unlabeled samples for labeling.
problem Efficiently label unlabeled data in applications with scarce labeled data.
method Formulated as open-set recognition, uses VNNs to identify uncertain samples.
result Achieved state-of-the-art results on MNIST, CIFAR-10, and CIFAR-100.
Improved Thompson Sampling for logistic bandits with information-theoretic analysis.
problem Optimizing binary reward probabilities in logistic bandit problems.
method Information-theoretic framework, focusing on the information ratio and minimax measure.
result Bound on Bayesian expected regret of O ( d / α T log ( β T / d ) ) O(d/α\sqrt{T \log(βT/d)}) O ( d / α T log ( β T / d ) ) for logistic bandits. New MI bounds improve estimation in deep generative models.
problem Estimating mutual information without density information is intractable.
method Importance sampling, Annealed Importance Sampling, Generalized IWAE, MINE-AIS.
result Improved bounds for estimating mutual information in deep models.
Study shows a tradeoff between sample complexity and computational efficiency for learning halfspaces with random noise.
problem PAC learning γ-margin halfspaces with Random Classification Noise.
method Established an information-computation tradeoff and provided a simple efficient algorithm with sample complexity O(1/(γ^2 ε^2)). Also, proved lower bounds for SQ algorithms and low-degree polynomial tests.
result Inherent gap between sample complexity and computational efficiency for learning halfspaces with random noise.
Contextual information helps identify the best arm more efficiently.
problem Best arm identification with contextual covariate information.
method Proposed a context-aware version of the 'Track-and-Stop' strategy.
result Expected number of arm draws matches lower bound asymptotically.
New bounds on IDS for RL show how to balance computation and learning efficiency.
problem Understanding and optimizing information-directed sampling (IDS) for reinforcement learning.
method Developed novel information-theoretic tools to bound information ratio and cumulative information gain.
result Derived prior-free Bayesian regret bounds for IDS in tabular finite-horizon MDPs and improved computational efficiency.
New method improves robustness of Bayesian experimental design.
problem Bayesian experimental design's sensitivity to prior distribution changes.
method Introduces robust expected information gain (REIG) and uses KL-divergence ambiguity sets.
result REIG stabilizes sampling-based EIG estimation and compensates for prior variability.
Privileged Information Dropout improves RL performance without distillation.
problem Improving sample efficiency and performance in reinforcement learning.
method Introducing Privileged Information Dropout to directly incorporate privileged information into RL agent inputs.
result Privileged Information Dropout outperforms distillation and auxiliary tasks in a partially-observed environment.