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.
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.
New pricing algorithm learns demand curves and optimizes prices in dynamic markets.
problem Dynamic pricing in markets with incomplete demand information and shifting conditions.
method Actor-Critic Information-Directed Pricing (ACIDP) using IDS algorithms and auditing procedures.
result ACIDP outperforms UCB and TS in market environment shifts.
Unified algorithm for efficient pure exploration using dual variables.
problem Efficiently achieving a specific goal through adaptive experimentation.
method Introducing dual variables to derive optimal allocation conditions, leading to Information-Directed Selection.
result Top-two Thompson sampling attains asymptotic optimality for Gaussian best-arm identification.
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.
DCGANs generate drainage networks quickly from samples.
problem High computational costs in generating large numbers of drainage networks.
method DCGANs trained with connectivity-informed directional information.
result Connectivity-informed DCGANs outperform other methods in reproducing accurate drainage networks.
This work improves online SGD's sample complexity for multi-index models by considering higher-order terms.
problem Suboptimal sample complexity for learning multi-index models using online SGD.
method Focus on both second- and higher-order terms to improve sample complexity.
result Online SGD achieves ildeO(dPL−1) samples for multi-index models. 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.
ASD algorithm maximizes model estimates by adaptively labeling points.
problem Maximizing model estimates through adaptive labeling of points in a sequential decision-making problem.
method Formulated a general information-directed sampling (IDS) algorithm with theoretical guarantees for linear, graph, and low-rank models.
result IDS algorithm outperforms in both simulation and real-data experiments for discovering chemical reaction conditions.
Algorithm for sequential user-product rating prediction in recommender systems.
problem Predicting ratings in a sequential user-product rating prediction setting.
method Gamma process factor model with Thompson Sampling and Information-Directed Sampling.
result Information-Directed Sampling achieves state-of-the-art performance.
New sampling methods improve performance in stochastic bandits with graph feedback.
problem Stochastic multi-armed bandit problems with graph feedback.
method Information Directed Sampling (IDS) policies for graph-aware decision making.
result IDS policies provide tighter regret bounds than existing methods.
IDS improves reinforcement learning with contextual information.
problem Optimizing IDS for contextual reinforcement learning.
method Investigated contextual bandit problems and proposed a computationally-efficient IDS.
result Contextual IDS outperforms conditional IDS by considering future contexts.
Proposes a neural network model to improve predictions in biased datasets.
problem Reduces bias in predictions from datasets with selection bias.
method Integrates meta information about bias direction and quantity into a neural network model.
result Improves prediction accuracy in electoral polls with biased training data.
Order-flow entropy predicts price magnitude without directionality.
problem Predicting price magnitude in financial markets.
method Real-time order-flow entropy computed from a 15-state Markov transition matrix.
result Order-flow entropy predicts the magnitude of intraday returns with high accuracy.
New approach for bandits with noise dependent on evaluation points, improving on existing methods.
problem Stochastic bandit problem with heteroscedastic noise.
method Introduces Information Directed Sampling (IDS) and proves high-probability regret bounds.
result New high-probability regret bounds for general policies, including IDS.
Novel approach for SEM in small samples with p>n.
problem Small sample size and p>n issues in factor-based SEM. method Reformulates covariance structure into self-covariance and cross-covariance, defines a feasible set with relative error constraint.
result Improved stability and directional information in small-sample settings.
Direct sum result for information complexity in PAC learning.
problem Minimum information required for consistent and proper learning.
method Introduced a class of functions with information complexity and proved a direct sum result.
result Direct sum result for information complexity in PAC learning.
Bayesian optimization improved for biased data.
problem Adversarial bias in observations, especially hidden confounders.
method Reduction to dueling bandits, information-directed sampling (IDS).
result First efficient kernelized algorithm with regret guarantees.
Optimal sample complexity for learning DDAGs from noisy data.
problem Learning interactions in linear dynamical systems over DAGs.
method Proposed a metric and algorithm based on PSD matrix for reconstruction.
result Optimal sample complexity n=Θ(qlog(p/q)) for learning DDAGs. A new method for optimization in probability space using Newton's flows.
problem Optimization in probability space with information metrics.
method Information Newton's flows, including Fisher-Rao and Wasserstein-2 metrics, with Newton's Langevin dynamics and variational methods.
result Effective numerical implementation and convergence results for the proposed method.
Ranking stock indices based on causal influence using directed information graphs.
problem Identifying which countries exert the most economic influence in a subset of the global economy.
method Representing indices as nodes in a directed graph, estimating causal influences using directed information functional, ranking indices based on net-flow.
result Indices representing smaller economies can exert significant influence on larger economies.
Paper solves NGCA for discrete distributions using LLL method.
problem Learning hidden non-Gaussian components in discrete distributions.
method Utilizes LLL lattice basis reduction method.
result Sample and computationally efficient algorithm for NGCA in discrete distributions.
Hypermodels improve exploration efficiency and accuracy.
problem Efficiently approximating Thompson sampling with large ensembles.
method Introducing hypermodels as a generalization of ensembles, including linear and neural network hypermodels.
result Hypermodels enable more accurate exploration and performance gains over Thompson sampling.
We propose a graphical model for representing networks of stochastic processes, the minimal generative model graph. It is based on reduced factorizations of the joint distribution over time. We show that under appropriate conditions, it is unique and consistent with another type of graphical model, the directed informa…
A new algorithm STE for model-based RL improves learning rates.
problem Sparse rewards and computational intractability of estimating information gain.
method Developed a novel algorithm based on Stein Information Directed Exploration (STE)E.
result Achieves sublinear Bayesian regret, outperforming prior approaches.
IDS optimizes regret in stochastic partial monitoring with linear rewards.
problem Optimizing decision-making in uncertain environments with linear rewards.
method Information Directed Sampling (IDS) for stochastic partial monitoring.
result Achieves optimal regret rates in all observable game regimes.
Direct policy gradients optimize policies in discrete action spaces using sampling.
problem Optimizing policies in discrete action spaces with direct methods.
method Combining direct optimization and A⋆ sampling for policy gradient approximation. result DirPG algorithms can incorporate domain knowledge and have higher probability of sampling informative gradients.
Sum-of-Squares lower bound shows NGCA requires more samples than known algorithms.
problem Finding a non-Gaussian direction in a high-dimensional dataset.
method Sum-of-Squares (SoS) framework to prove lower bounds.
result First super-constant degree SoS lower bound for NGCA.
Study examines line search approximations for neural networks using MBSS.
problem Reducing computational cost in training large-scale neural networks.
method Empirical study of quadratic line search approximations for dynamic MBSS loss functions, enforcing different types of function and derivative information.
result Selectively enforcing information in approximations reduces the variance of predicted step sizes.
MineRL Competition reduced reinforcement learning sample needs.
problem Sample inefficiency in reinforcement learning.
method Human demonstrations and imitation learning integrated into reinforcement learning algorithms.
result Top solutions used deep reinforcement learning and imitation learning.
IDS improves exploration in deep reinforcement learning.
problem Efficient exploration in reinforcement learning, especially with heteroscedastic returns.
method Information-Directed Sampling (IDS) for deep Q-learning.
result Significant improvement in Atari game performance over alternative approaches.
Motivation: Algorithms that discover variables which are causally related to a target may inform the design of experiments. With observational gene expression data, many methods discover causal variables by measuring each variable's degree of statistical dependence with the target using dependence measures (DMs). Howev…
EPSTE: A geometric token and deep learning approach to estimating transfer entropy in neuroimaging time series
problem Inferring directed interactions between neural systems from EEG and MEG
method Reframing TE estimation as a learnable problem operating on structured symbolic representations
result EPSTE achieves near-perfect recovery of ground-truth directed structure and significantly lower absolute error than the baseline
Top-two algorithm improved for best-k-arm selection.
problem Best-k-arm identification in multi-armed bandits.
method Information-directed selection based on dual variables.
result Top-two Thompson sampling with IDS is asymptotically optimal.
SAUNA filters out noisy samples to boost RL performance.
problem Improving RL performance by filtering out non-informative samples.
method SAUNA selects samples based on the fraction of variance explained by the value function, rejecting non-informative transitions.
result SAUNA significantly improves RL performance on benchmark problems.
Dimension reduction of multivariate data supervised by auxiliary information is considered. A series of basis for dimension reduction is obtained as minimizers of a novel criterion. The proposed method is akin to continuum regression, and the resulting basis is called continuum directions. With a presence of binary sup…
DEDACT breaks down feature importance into direct and associative components.
problem Lack of clear distinction between direct and associative feature importance.
method DEDACT framework to decompose direct and associative importance measures.
result Provides insight into sources of prediction-relevant information and feature pathways.
This work investigates how gradient-based learning performs with structured data, revealing issues and improvements.
problem Gradient-based learning under structured data, particularly with a spiked covariance structure.
method Investigates the effect of a spiked covariance structure on gradient-based feature learning and proposes weight normalization.
result Gradient-based dynamics may fail to recover the true direction in anisotropic settings, but weight normalization can improve performance.
Direct learning framework for integrating multi-source causal data.
problem Conditional average treatment effects inference from heterogeneous data.
method Direct learning framework, double robustness, causal information-aware weighting function.
result Effective causal data fusion in both homogeneous and heterogeneous scenarios.
This paper reviews information theory in open-world machine learning.
problem Lack of a unified theoretical foundation for open-world machine learning.
method Synthesis of information theoretic approaches.
result Established a pathway toward provable and trustworthy open world intelligence.
New IDS algorithm refines parameter norm bounds for better bandit performance.
problem Frequentist IDS requires tight norm bounds, which are often unavailable in practice.
method Iteratively refines a high-probability upper bound on true parameter norm using data.
result Regret bounds independent of assumed parameter norm, outperforming state-of-the-art algorithms.
New method preserves directed edge info in graph embeddings.
problem Learning accurate node embeddings for directed graphs.
method Low-rank asymmetric projections with graph likelihood objective.
result Significant improvement in link prediction accuracy.
Paper introduces a method for continual learning using online leverage scores.
problem Avoiding forgetting and interference of previous knowledge in continual learning.
method Uses statistical leverage scores to measure data importance and a frequent directions approach for online continual learning.
result Demonstrates effectiveness in avoiding catastrophic forgetting and computational efficiency.
A new distance measure balances projection exploration and informativeness.
problem Inefficient and incomplete projection sampling in existing sliced-Wasserstein distances.
method Proposes Distributional Sliced-Wasserstein (DSW) that optimally balances projection exploration and informativeness.
result DSW generalizes Max-SW and can be computed efficiently.
New method estimates spin system mutual information using neural networks.
problem Estimating mutual information in spin systems.
method Monte Carlo sampling enhanced by autoregressive neural networks.
result Area law satisfied for temperatures away from critical temperature.
Study of curves and surfaces from single-direction projections.
problem Obtaining complete shape information from a single view.
method Theoretical study of differential geometric information from multiple orthogonal projections.
result Formulae for recovering certain information on curves or surfaces from their projections.
A new geometric concept, the dead direction, bridges singular learning theory and information geometry.
problem The gap between singular learning theory and information geometry.
method Introducing the dead direction, a unit vector along degenerating Fisher metric, and showing its KL order can be recovered.
result The KL order of the dead direction can be recovered as the decay rate of the directional Fisher curvature, providing a handle on singular geometry.