This work analyzes generalization in federated learning using information theory.
problem Generalization performance in federated learning is less explored compared to centralized learning.
method The work applies an information-theoretic analysis via the conditional mutual information (CMI) framework to study federated learning's two-level generalization.
result The work derives multiple CMI-based bounds, including hypothesis-based CMI bounds and fast-rate evaluated CMI bounds, which improve convergence rates for specific model aggregation strategies and structured loss functions.
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.
cMIM improves representation learning without positive-pair augmentations.
problem Learning robust representations for diverse tasks.
method Contrastive Mutual Information Machine (cMIM) framework.
result cMIM outperforms MIM and InfoNCE on classification and regression tasks.
New bounds on machine learning data leakage identified.
problem Machine Learning models can leak sensitive information.
method Formalized attack setups, derived universal bounds, studied mutual information.
result Connected attack success rate to generalization gap and mutual information.
Machine learning theory has mostly focused on generalization to samples from the same distribution as the training data. Whereas a better understanding of generalization beyond the training distribution where the observed distribution changes is also fundamentally important to achieve a more powerful form of generaliza…
A new method is proposed to compute connectivity measures on multivariate time series with gaps. Rather than removing or filling the gaps, the rows of the joint data matrix containing empty entries are removed and the calculations are done on the remainder matrix. The method, called measure adapted gap removal (MAGR), …
Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information, which is often interpreted as a regularizer that controls the degree of compression. We here examine whether inclusion of the rate also acts…
A new method improves model generalization by recognizing representations.
problem Generalization issues in existing Information Bottlenecks.
method Recognizable Information Bottleneck (RIB) using f-CMI and density ratio matching.
result Improves model generalization through recognizability regularization.
Forecastability measures predictive information across horizons.
problem How much predictive information is available at each prediction horizon?
method Develops the consequences of mutual information between future observations and information set.
result Forecastability is a profile reflecting process dependence structure, with properties like compression and truncation error.
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.
A method removes treatment-covariate dependence for counterfactual prediction without adversarial training.
problem Counterfactual prediction under assignment bias.
method Information-theoretic approach learning a stochastic representation Z to minimize mutual information with outcomes.
result The method performs favorably in likelihood, counterfactual error, and policy evaluation compared to adversarial baselines.
Novel framework optimizes experiments for implicit models using mutual information.
problem Optimizing experiments for intractable implicit models.
method Sequential Bayesian Experimental Design using Mutual Information.
result Framework efficiently estimates parameters with few iterations.
New framework explains data augmentation's role in machine learning.
problem Understanding how data augmentation affects generalization and invariance learning.
method Information-theoretic framework based on mutual information bounds and orbit-averaged loss functions.
result Derives a new generalization bound decomposing the generalization gap into three interpretable terms.
Theory proposes neural networks can be initialized for optimal information transmission.
problem Optimizing neural networks for optimal information transmission and representation.
method Developed a corrected mean-field framework to study neural networks as information channels, proving mutual information maximization at dynamic isometry.
result Mutual information maximization is realized between inputs and propagated signals when neural networks are initialized at dynamic isometry.
New neural network approach using mutual information.
problem Training neural networks for imbalanced datasets.
method Converts neural network classifiers to mutual information evaluators.
result New form of softmax leads to better classification accuracy, especially for imbalanced datasets.
Paper describes profiles of multivariate normal distributions and novel estimators for mutual information.
problem Estimating mutual information for complex distributions.
method Analytical description of profiles, introduction of Bend and Mix Models, Monte Carlo estimation.
result Bend and Mix Models accurately estimate mutual information profiles and provide Bayesian estimates.
This paper improves disentanglement in VAEs by progressively learning hierarchical representations.
problem Compromised disentanglement in VAEs due to high-level abstraction extraction.
method Progressive learning of independent hierarchical representations from high to low levels.
result Improved disentanglement demonstrated on two benchmark datasets using new metrics.
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.
Paper benchmarks mutual info estimators on diverse distributions.
problem Evaluating mutual information estimators on complex, real-world distributions.
method Constructs a diverse family of known-ground truth distributions, proposes a benchmark platform.
result Highlights differences in classical and neural estimators' performance across various conditions.
The paper argues that normalized mutual information is biased in clustering and community detection.
problem Bias in normalized mutual information for clustering and community detection.
method Introducing a modified version of mutual information to correct for information content and spurious dependence.
result The modified mutual information leads to different conclusions about which algorithms are best for community detection.
Neural estimator improves mutual information estimation in high dimensions.
problem Estimating mutual information in high dimensions is challenging.
method Parametrizing conditional densities with normalizing flows and using block autoregressive structure.
result Improved mutual information estimation on benchmark tasks.
We find the maximum mutual information for neural networks and its key determinants.
problem Understanding the maximum mutual information in neural architectures.
method Derived closed-form expression for maximum mutual information across neural network families.
result Maximum mutual information stems from a generalized formula and is influenced by network width and statistical invariances.
This paper bounds meta-generalization gap using information theory.
problem Improving sample efficiency for new tasks in meta-learning.
method Information-theoretic upper bounds on meta-generalization gap for two meta-learning classes.
result Novel ITMI bounds for noisy iterative algorithms.
Measuring mutual information from finite data is difficult. Recent work has considered variational methods maximizing a lower bound. In this paper, we prove that serious statistical limitations are inherent to any method of measuring mutual information. More specifically, we show that any distribution-free high-confide…
Improved method for encoding contingency tables reduces mutual information bias.
problem Mutual information bias in measuring label similarity.
method Improved method for encoding contingency tables to reduce information cost.
result Better bound on reduced mutual information in typical use cases.
This study tackles mutual fund portfolio prediction, focusing on novel items.
problem Predicting novel items in mutual fund portfolios is challenging and less explored.
method Created a comprehensive benchmark dataset and evaluated various recommender system models.
result Autoencoder-based approaches outperform state-of-the-art models in predicting novel items.
Proposes a new bound on generalization error using conditional mutual information.
problem Improving the generalization error bound in machine learning.
method Combines error decomposition and conditional mutual information techniques.
result New bound is order-wise better than previous ones in a simple Gaussian setting.
The paper introduces submodular information measures for machine learning applications.
problem Generalizing information-theoretic measures to non-random variables.
method Developing combinatorial information measures based on submodular functions.
result Submodular mutual information is submodular in one argument for certain submodular functions.
Proposes a framework to maximize mutual information in VAE models for better latent code representation.
problem Lack of explicit measurement of the quality of learned representations in VAE models.
method Variational Mutual Information Maximization Framework for VAE.
result Maximizes mutual information between latent codes and observations, improving latent code representation.
We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/decoder framework. Our key principles are symmetry and mutual information, where symmetry encourages the encoder and decoder to learn differe…
A new method estimates mutual information using neural classifiers.
problem Estimating mutual information for high-dimensional data is challenging.
method Trains a classifier to estimate joint distribution probability.
result Demonstrates high accuracy and reduces variance compared to variational methods.
New estimator improves mutual information estimation.
problem Estimating mutual information in data science and machine learning.
method Proposes a new estimator that uses a preliminary estimate of the data distribution.
result A preliminary estimate helps in estimating mutual information more accurately.
The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
problem Learning structured representations from unlabeled data.
method Adversarial maximization of mutual information between a structured latent variable and a target variable.
result The proposed method outperforms current baselines in document hashing and yields highly compressed interpretable representations.
Paper proposes mutual information learning for deep learning classifiers.
problem Overfitting in deep learning models.
method Mutual information learning framework to train classifiers.
result MILCs achieve better generalization than conditional entropy classifiers.
TCMI assesses mutual dependence of continuous variables without parametric assumptions.
problem Estimating mutual information from continuous distributions.
method TCMI extends mutual information to continuous variables using cumulative distributions.
result TCMI facilitates feature selection and ranking of variable sets.
We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks. We present a Mutual Information Neural Estimator (MINE) that is linearly scalable in dimensionality as well as in sample size, trainable through back-prop, an…
Reshef et al. recently proposed a new statistical measure, the "maximal information coefficient" (MIC), for quantifying arbitrary dependencies between pairs of stochastic quantities. MIC is based on mutual information, a fundamental quantity in information theory that is widely understood to serve this need. MIC, howev…
Sequence models assign probabilities to variable-length sequences such as natural language texts. The ability of sequence models to capture temporal dependence can be characterized by the temporal scaling of correlation and mutual information. In this paper, we study the mutual information of recurrent neural networks …
Active feature selection uses mutual information to choose fewer labels for better feature selection.
problem Selecting features with limited labeled data.
method Uses active feature selection with mutual information criterion, optimizing label selection for better feature quality.
result Algorithm selects features with higher mutual information using fewer labels than the data set size.
In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data. Applied on language modelling, our regularizer expresses the inductive bias that sequence variables should have high mutual information even though the model might not see abundant observations for complex lo…
In this paper, we present a new approach to interpret deep learning models. By coupling mutual information with network science, we explore how information flows through feedforward networks. We show that efficiently approximating mutual information allows us to create an information measure that quantifies how much in…
This paper improves DNN generalization by accurately estimating mutual information.
problem Intractability of estimating mutual information in DNNs.
method Introduces a probabilistic representation of DNNs to accurately estimate mutual information.
result Derives a tighter generalization bound than previous relaxations.
Novel mutual information bound improves statistical inference rates.
problem Improving statistical inference rates in Bayesian nonparametrics.
method Introduces a novel mutual information bound.
result Improved contraction rates for fractional posteriors.
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.
InfoBridge uses diffusion bridges to estimate mutual information accurately.
problem Estimating mutual information between random variables.
method Formulated mutual information estimation as a domain transfer problem using diffusion bridge models.
result Demonstrated unbiased estimator for various data types.
New framework controls generalization for heavy-tailed data in RLHF and SGLD.
problem Heavy-tailed data in modern learning pipelines.
method Tail-dependent information-theoretic framework for sub-Weibull data.
result Sharp generalization bounds for heavy-tailed data.
Mutual information is widely applied to learn latent representations of observations, whilst its implication in classification neural networks remain to be better explained. We show that optimising the parameters of classification neural networks with softmax cross-entropy is equivalent to maximising the mutual informa…
New method estimates mutual information using normalizing flows.
problem Mutual information estimation in high-dimensional data.
method Normalizing flows to map data to target distributions with known MI.
result Theoretical guarantees and practical advantages demonstrated.