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.
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.
New tighter bounds for learning algorithms from Steinke & Zakynthinou's supersample setting.
problem Improving generalization bounds for machine learning algorithms.
method Information-theoretic approach using projected loss and Rademacher sequence.
result The new bounds are tighter than previous information-theoretic bounds.
Optimistic algorithms and Thompson sampling use info-theory for better reinforcement learning.
problem Designing algorithms that balance exploration and exploitation in reinforcement learning.
method Integrating information-theoretic concepts into optimistic algorithms and Thompson sampling.
result Cumulative regret bound depends on uncertainty and quantifies prior information value.
The paper explores the information-theoretic nature of excess risk in machine learning.
problem Understanding the excess risk in machine learning models.
method Formulates the minimax excess risk as a zero-sum game and modifies it to allow swapping of the order of play.
result Proves that under certain conditions, the duality gap is zero, allowing for the application of Bayesian results to provide bounds on minimax excess risk.
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.
Unified notation simplifies information-theoretic concepts in machine learning.
problem Opaque notation for information-theoretic quantities in machine learning.
method Proposed a practical and unified notation for information-theoretic quantities.
result Unified notation facilitates new intuitions and rederivations in machine learning.
New analysis improves generalization bounds for meta-learning.
problem Improving generalization in meta-learning algorithms.
method Information-theoretic analysis of MAML and its stochastic variant.
result Data-dependent generalization bound is tighter and non-vacuous.
Unified framework for information-theoretic bounds on learning algorithms.
problem Deriving generalization bounds for learning algorithms.
method Probabilistic decorrelation lemma, symmetrization, couplings, chaining, Young's inequality.
result New upper bounds on generalization error in expectation and high probability.
Paper analyzes ECE bias and provides bounds for its estimation.
problem Understanding the estimation bias in ECE for machine learning models.
method Information-theoretic approach to analyze bias in uniform mass and uniform width binning strategies.
result Established upper bounds on ECE estimation bias and optimal number of bins.
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.
A principle for specialized decision-making divides complex problems into manageable parts.
problem Complex decision-making problems beyond individual capabilities.
method An on-line learning rule that learns a partitioning of the problem space for specialized linear policies.
result The approach solves problems that exceed individual decision-makers' capabilities.
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.
Unified framework improves meta-learning generalization bounds.
problem Limited sharpness of existing meta-generalization bounds.
method Unified information-theoretic derivation for single-step bounds.
result Unified bounds exhibit tighter scaling and computational advantages.
PRI-VAE learns disentangled representations by optimizing principle-of-relevant-information.
problem Learning disentangled representations under VAE framework remains unknown.
method Proposes PRI-VAE, a novel learning objective to optimize disentanglement.
result Demonstrates effectiveness of PRI-VAE on four benchmark datasets.
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.
In this paper, we study the information-theoretic limits of learning the structure of Bayesian networks (BNs), on discrete as well as continuous random variables, from a finite number of samples. We show that the minimum number of samples required by any procedure to recover the correct structure grows as Ω(m) and $Ω…
Proposes a new information-theoretic framework for analyzing deep neural networks.
problem Difficulty in analyzing deep neural networks using existing theoretical frameworks.
method Introduces an information-theoretic framework with new notions of regret and sample complexity.
result Establishes sample complexity bounds for deep neural networks that are width-independent and linear in depth.
The paper connects mirror descent, Thompson sampling, and information ratio in online learning.
problem Analyzing and improving regret guarantees in online learning algorithms.
method Combining information-theoretic analysis with minimax duality and mirror descent techniques.
result An efficient algorithm with matching regret guarantees for adversarial bandits and improved guarantees for other settings.
Stochastic volatility models describe asset prices St as driven by an unobserved process capturing the random dynamics of volatility σt. Here, we quantify how much information about σt can be inferred from asset prices St in terms of Shannon's mutual information I(St:σt). This motivates a careful nume…
Unified framework for removing unwanted information from machine learning models.
problem Removing undesirable features or data points from machine learning models while preserving utility.
method Information-theoretic regularization approach for data point and feature unlearning.
result Unified mathematical framework with provable guarantees for both data point and feature unlearning.
Neural networks learn complex functions efficiently near information-theoretic limits.
problem Understanding how neural networks learn high-dimensional features.
method Gradient descent learning of a Gaussian Multi-index model with hidden subspace.
result A standard two-layer neural network can learn the target with optimal sample and time complexity.
New method explains sensitivity of test data uncertainty in Bayesian inference.
problem Widespread belief that test data similarity reduces epistemic uncertainty.
method Information-theoretic decomposition of predictive uncertainty.
result Defines sensitivity using information-theoretic quantities.
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.
Develops a method to evaluate model consistency with data using information theory.
problem Evaluating the consistency of a model with observed data.
method Information-theoretic approach based on model's ability to generate similar data.
result The method can be used for sequential and nonlinear data, and is validated on synthetic and real data.
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.
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.
Unified information-theoretic objectives for training deep neural networks.
problem Difficulty in computing information-theoretic quantities for large deep neural networks.
method Review and unify competing objectives, develop surrogate objectives.
result Surrogate objectives allow applying information bottleneck to modern neural network architectures.
New bounds for Thompson Sampling with many actions using rate-distortion theory.
problem Dependence of regret on prior uncertainty through entropy for many actions.
method Information-theoretic analysis with rate-distortion theory.
result Established new bounds that depend on rate-distortion instead of entropy.
Proof of Gaussian ML estimator consistency in linear auto-regressive models.
problem Consistency of Gaussian maximum likelihood estimator in linear auto-regressive models.
method Information-theoretic proof without stability assumptions.
result Nearly optimal non-asymptotic rates for parameter recovery.
New research shows existing information-theoretic methods can't establish minimax rates for gradient descent in stochastic convex optimization.
problem Establishing minimax rates for gradient descent in stochastic convex optimization using information-theoretic methods.
method Examined several information-theoretic frameworks including input-output mutual information bounds, conditional mutual information bounds, PAC-Bayes bounds, and their variants.
result Proved that none of the examined information-theoretic frameworks can establish minimax rates for gradient descent in stochastic convex optimization.
Feature selection is one of the most fundamental problems in machine learning. An extensive body of work on information-theoretic feature selection exists which is based on maximizing mutual information between subsets of features and class labels. Practical methods are forced to rely on approximations due to the diffi…
Develops a fast Bayesian optimisation method that reduces computational overhead.
problem Computational inefficiency and restrictive kernel choices in information-theoretic Bayesian optimisation.
method FITBO method that avoids sampling the global minimizer and allows for more flexible kernel choices.
result Demonstrates that FITBO inherits performance from information-theoretic Bayesian optimisation but is faster.
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.
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.
EDL discovers state-covering skills without relying on task rewards.
problem Discovering skills in reinforcement learning without a task-oriented reward function.
method EDL optimizes information-theoretic objective using different machinery to address coverage problem.
result EDL discovers state-covering skills more effectively than existing methods.
In this paper we consider an information theoretic approach for the accounting classification process. We propose a matrix formalism and an algorithm for calculations of information theoretic measures associated to accounting classification. The formalism may be useful for further generalizations and computer-based imp…
The study bounds generalization error using mutual information and proposes methods to control it.
problem Understanding and controlling the generalization capability of learning algorithms.
method Derives upper bounds on generalization error using mutual information, proposes regularization methods.
result Provides theoretical guidelines for balancing data fit and generalization.
The paper examines FDL and SF algorithms using information bottleneck theory.
problem Understanding the behavior of FDL algorithms using information-theoretic terms.
method Formalization of FDL in information-theoretic terms, using information planes to analyze SF algorithm.
result Empirical support for the conjecture about the dynamics of FDL.
We propose a general information-theoretic approach called Seraph (SEmi-supervised metRic leArning Paradigm with Hyper-sparsity) for metric learning that does not rely upon the manifold assumption. Given the probability parameterized by a Mahalanobis distance, we maximize the entropy of that probability on labeled data…
Study uses information-theoretic measures to analyze neural networks and neuron importance.
problem Understanding the importance of individual neurons in neural networks.
method Cumulative ablation of neurons, analyzing entropy, mutual information, and class selectivity.
result Class selectivity is not a good indicator for classification performance, while mutual information and selectivity are positively correlated with performance.
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.
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.
This work improves generalisation bounds using chaining and information theory.
problem Improving generalisation bounds for supervised learning algorithms.
method Developed a theoretical framework linking generalisation bounds to their chained counterparts, derived new bounds using Wasserstein distance.
result Chained generalisation bounds can be tighter than standard bounds, especially for concentrated hypothesis distributions.
Bayesian approach scores influential training examples for model predictions.
problem Enhance interpretability and safety of machine learning models.
method Formulate TDA as a Bayesian information-theoretic problem, scoring subsets by information loss.
result Method aligns with classical influence scores while promoting diversity for subsets.
Improved bounds for SGLD via data-dependent estimates.
problem Improving generalization bounds for noisy iterative learning algorithms.
method Variational characterization of mutual information and data-dependent priors.
result Significantly improved mutual information bounds for SGLD.
Information theoretic active learning has been widely studied for probabilistic models. For simple regression an optimal myopic policy is easily tractable. However, for other tasks and with more complex models, such as classification with nonparametric models, the optimal solution is harder to compute. Current approach…
Novel kernelized Renyi's entropy improves deep learning generalization bounds.
problem Improving generalization bounds for deep learning algorithms.
method Kernelized Renyi's entropy, a new information theoretical measure.
result Theoretical bounds are tighter than current SOTA results.