Framework for understanding overfitting and underfitting using information theory.
problem Understanding and preventing overfitting and underfitting in machine learning.
method Information-theoretic framework measuring algorithm capacity and dataset information transfer.
result Upper-bounding algorithm capacity and establishing its relationship to machine learning quantities.
There are (at least) three approaches to quantifying information. The first, algorithmic information or Kolmogorov complexity, takes events as strings and, given a universal Turing machine, quantifies the information content of a string as the length of the shortest program producing it. The second, Shannon information…
Meta learning with information theory and Gaussian processes.
problem Few-shot learning problems.
method Information bottleneck, mutual information, variational approximations, Gaussian processes.
result Competitive accuracy on few-shot classification problems.
The IB theory explains how ML systems reduce data dimensions while preserving predictive power.
problem Understanding how machine learning systems reduce data dimensions effectively.
method Information-theoretic approach using mutual information.
result The best representation T maximally informs Y while minimizing mutual information with X. New bounds estimate learning algorithm performance using prediction information.
problem Estimating the performance of black-box learning algorithms.
method Information-theoretic bounds based on prediction information.
result Improved bounds applicable to deterministic algorithms and easier to estimate.
The paper establishes bounds for transductive learning using information theory.
problem Transductive learning generalization gap control.
method Information theory, PAC-Bayes, mutual information, conditional mutual information, different information measures.
result Established transductive information-theoretic and PAC-Bayesian bounds.
The paper bounds generalization error for iterative learning with bounded updates.
problem Generalization error of iterative learning algorithms with bounded updates for non-convex loss functions.
method Information-theoretic techniques, reformulating mutual information as update uncertainty, variance decomposition.
result Improved generalization error bounds for iterative learning algorithms with bounded updates.
New theory explains forgetting in learning algorithms.
problem Tendency of learning algorithms to forget past knowledge.
method Proposes a self-consistency theory of forgetting as a loss of predictive information.
result Exact Bayesian inference allows for adaptation without forgetting.
New approach quantifies overfitting in high-dimensional regression.
problem Quantifying and avoiding overfitting in large neural networks.
method Information bottleneck theory to minimize residual information while maximizing relevant bits.
result Characterized the relative information efficiency of randomized regression compared to optimal algorithms.
Non-linear image reconstruction and signal analysis deal with complex inverse problems. To tackle such problems in a systematic way, I present information field theory (IFT) as a means of Bayesian, data based inference on spatially distributed signal fields. IFT is a statistical field theory, which permits the construc…
Paper introduces a novel error measure for neural networks integrating statistical and information theory.
problem No single error measure is universally best for neural network training.
method Developed a novel error measure EExpAbs and integrated it into the Levenberg-Marquardt algorithm. result Self-adaptive, dynamic learning algorithm improves both model accuracy and training process.
The article introduces inferential moments for analyzing uncertain multivariable systems.
problem Handling inference tasks in uncertain multivariable systems.
method Bayesian inference and quantification of inferential moments.
result Quantification of inferential moments and their connection to mutual information.
The ability to integrate information in the brain is considered to be an essential property for cognition and consciousness. Integrated Information Theory (IIT) hypothesizes that the amount of integrated information (Φ) in the brain is related to the level of consciousness. IIT proposes that to quantify information i…
We consider the "partial information decomposition" (PID) problem, which aims to decompose the information that a set of source random variables provide about a target random variable into separate redundant, synergistic, union, and unique components. In the first part of this paper, we propose a general framework for …
Paper studies community detection in censored hypergraphs using information theory.
problem Community detection in censored hypergraphs with missing values.
method Information-theoretic approach, polynomial-time algorithm, spectral algorithm with refinement.
result Derives information-theoretic threshold for exact recovery of community structure.
In this paper, we examine the fundamental performance limits of prediction, with or without side information. More specifically, we derive generic lower bounds on the Lp norms of the prediction errors that are valid for any prediction algorithms and for any data distributions. Meanwhile, we combine the ent…
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 applies information theory to financial markets, improving risk management and asset allocation.
problem Improving risk management and asset allocation in financial markets.
method Information-theoretic measures (entropy, mutual information, etc.) applied to financial time series.
result Normalized mutual information (NMI) is a powerful measure of temporal dependence in financial markets.
We analyze Gibbs-based transfer learning algorithms using information theory.
problem Understanding the generalization error of transfer learning.
method Information-theoretic analysis focusing on α-weighted-ERM and two-stage-ERM. result Exact characterization of generalization behavior using conditional symmetrized KL information.
New framework converts offline to online estimation using black-box offline estimators.
problem Convert offline estimation algorithms to online estimation algorithms.
method Oracle-Efficient Online Estimation (OEOE) framework.
result Achieves near-optimal online estimation error via black-box offline estimators.
The Normalized Mutual Information (NMI) has been widely used to evaluate the accuracy of community detection algorithms. However in this article we show that the NMI is seriously affected by systematic errors due to finite size of networks, and may give a wrong estimate of performance of algorithms in some cases. We gi…
Random forests are a type of ensemble method which makes predictions by combining the results of several independent trees. However, the theory of random forests has long been outpaced by their application. In this paper, we propose a novel random forests algorithm based on cooperative game theory. Banzhaf power index …
New bounds improve neural network generalization through slicing.
problem Difficulty in evaluating mutual information in high dimensions for neural networks.
method Slicing the parameter space and using disintegrated mutual information and k-sliced mutual information.
result Slicing improves generalization and offers significant computational and statistical advantages.
New bounds tighten the generalization error of Gibbs algorithm.
problem Bounding the generalization error of Gibbs algorithm.
method Characterization of generalization error in terms of symmetrized KL information.
result Exact characterization of Gibbs algorithm's expected generalization error.
New approach to learning kernels from data using AIT principles.
problem Learning kernels from data in machine learning.
method Sparse Kernel Flows method based on AIT principles.
result Sparse Kernel Flows aligns with MDL principle and offers a robust theoretical foundation.
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.
The study analyzes transfer learning using information theory.
problem Transfer learning in different distributions.
method Information-theoretic analysis, focusing on KL divergence.
result Upper bounds for general transfer learning algorithms and specific ERM.
Study OOD generalization in meta-reinforcement learning using information theory.
problem Understanding how meta-reinforcement learning handles distribution shifts.
method Information-theoretic analysis of Markov Decision Processes and gradient-based algorithms.
result Established fine-grained generalization bounds for meta-reinforcement learning.
The paper applies Gaussianization to analyze Earth data, simplifying complex multivariate distributions.
problem Challenges in accurately estimating information content in high-dimensional, heterogeneous Earth data.
method Multivariate Gaussianization for robust probability density estimation.
result Validates the method for estimating information-theoretic measures in Earth system data.
New information-theoretic bounds improve machine learning generalization.
problem Improving machine learning generalization beyond traditional complexity-based methods.
method Introducing bounds using Wasserstein distance and structured methods to incorporate geometry and individual data dependence.
result Established connections between different bounds and introduced new tighter bounds for various loss functions.
Improved regret bounds for bandits with fixed expert advice using information theory.
problem Optimizing regret in bandit problems with fixed expert distributions.
method Information-theoretic analysis and KL-divergence measures.
result First regret bounds for EXP4 that can get arbitrarily close to zero under certain conditions.
Unified framework for active learning problems using information theory.
problem Combining level set estimation and Bayesian optimization.
method Information-theoretic criterion and acquisition function.
result Unified framework achieves state-of-the-art performance.
Theory of learning with weight-distribution constraints.
problem Understanding how structure influences function in neural networks.
method Statistical mechanical theory and optimal transport.
result Reduction in capacity due to constrained weight-distribution is related to Wasserstein distance.
Unified treatment of PAC-Bayesian and information-theoretic generalization bounds.
problem Generalization capabilities of machine learning algorithms.
method PAC-Bayesian and information-theoretic perspectives.
result Unified treatment and modular structure of proofs.
New compression theory justifies model pruning for neural networks.
problem Improving neural network performance with reduced model size.
method Information-theoretic rate-distortion theory applied to NN compression.
result Pruning improves model performance on CIFAR-10 and ImageNet datasets.
This paper uses information theory to improve risk modeling in big data.
problem Insufficient application of information theory in actuarial science.
method Explores information theory to uncover performance limits of insurance big data systems.
result Guidance for risk modeling and actuarial pricing systems.
The paper analyzes generalization of noisy iterative algorithms using communication theory.
problem Generalization of models trained by noisy iterative algorithms under different distributions.
method Connecting noisy iterative algorithms to additive noise channels in communication theory.
result Distribution-dependent generalization bounds for noisy iterative algorithms.
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.
Novel bounds for deep MDA algorithms improve performance and efficiency.
problem Improving performance of MDA algorithms with few target labels and pseudo labels.
method Information-theoretic tools and novel deep MDA algorithm.
result Algorithm-dependent generalization bounds for MDA.
Using frequency distributions of daily closing price time series of several financial market indexes, we investigate whether the bias away from an equiprobable sequence distribution found in the data, predicted by algorithmic information theory, may account for some of the deviation of financial markets from log-normal…
A novel framework infers causal direction from symbolic sequences using pattern entropy.
problem Challenges in discovering causal direction from temporal symbolic data.
method Dictionary Based Pattern Entropy (DPE) framework integrating AIT and Shannon Information Theory. result Minimizing pattern level uncertainty yields a robust framework for causal discovery.
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.
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.
Blackwell's theorems influence modern AI through information compression and decision making.
problem Information compression and decision making under uncertainty.
method Theorems developed in the 1940s and 1950s, applied to modern AI.
result Blackwell theorems remain relevant and influence modern AI subfields.
We adapt Shapley values to explain model uncertainty, connecting it to information theory.
problem Explaining uncertainty in model predictions.
method Adapted Shapley value framework to quantify feature contributions to predictive uncertainty.
result Deep connections between Shapley values and information theory quantities.
The paper develops sum-of-squares relaxations for computing f-divergences.
problem Computing f-divergences from non-centered covariance matrices. method Sum-of-squares relaxations for convex optimization.
result Sum-of-squares relaxations make computations tractable.
We present arguments for the formulation of unified approach to different standard continuous inference methods from partial information. It is claimed that an explicit partition of information into a priori (prior knowledge) and a posteriori information (data) is an important way of standardizing inference approaches …
Improved computational complexity in statistical models using second-order information.
problem Polynomial convergence of gradient descent in singular statistical models.
method Normalized Gradient Descent (NormGD) algorithm with second-order information.
result NormGD reaches final statistical radius in logarithmic iterations of n.