PAC-bayesian learning
PulseAugur coverage of PAC-bayesian learning — every cluster mentioning PAC-bayesian learning across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
New PAC-Bayesian method offers control certification for quadratic systems
Researchers have developed a new method using PAC-Bayesian bounds to certify quadratic closed-loop control systems. This approach addresses challenges with unbounded and non-Lipschitz loss functions by employing System …
-
New multi-distribution Rényi divergences characterized by researchers · 2 sources tracked
Researchers have characterized a new family of multi-distribution generalizations of Rényi divergences, which are crucial for comparing multiple probability distributions simultaneously. This new family, termed multi-wa…
-
New algebraic identity unifies information theory results
A new paper introduces a unified algebraic identity that connects various information-theoretic variational results. This identity generalizes classical formulas for entropy and divergence to multiple priors and holds f…
-
Paper: LLMs face fundamental limits as general-purpose solvers via prompting
A new paper argues that large language models (LLMs) are not truly general-purpose solvers due to fundamental constraints of prompt-based communication. The research suggests that language itself is a limited channel fo…
-
New paper questions LLM general-purpose learning limits due to language constraints
A new arXiv paper argues that large language models (LLMs) are not truly general-purpose learners due to fundamental constraints imposed by natural language as an interface. The research introduces the concepts of an "e…
-
New PAC-Bayes Derandomization Method for Smooth Loss Functions
Researchers have developed a new method for derandomizing PAC-Bayes generalization bounds, specifically for smooth loss functions. This approach aims to create high-probability bounds for deterministic predictors by lev…
-
New method predicts data distributions under drift and corruption
Researchers have developed a novel online learning method for predicting full data-generating distributions in non-stationary data streams, even when subjected to drift and adversarial corruption. The approach utilizes …
-
New research tackles deep learning uncertainty and generalization
Researchers are developing new methods to improve the reliability and understanding of deep learning models. One paper introduces Calibrated Variance Propagation (CVP) to provide accurate uncertainty estimates for trans…
-
New theory explains and improves test-time training for AI models
Researchers have developed a decision-theoretic framework to understand and improve test-time training (TTT), a method for adapting pretrained models to specific prompts. The new approach treats TTT as implicit Bayesian…
-
New PAC-Bayesian framework enhances adversarial robustness analysis for GNNs
Researchers have developed a new PAC-Bayesian framework to analyze the adversarial robustness of message passing graph neural networks (MPGNNs). This framework offers tighter generalization bounds by quantifying paramet…
-
New PAC-Bayes Theory Explains Gains from Symmetries in ML
Researchers have developed new theoretical guarantees for machine learning models that utilize symmetries, extending beyond compact groups and invariant data distributions. The study adapts and tightens existing bounds …
-
New papers explore GNNs for general use and reliable decision-making
Two new research papers explore advancements in Graph Neural Networks (GNNs). The first paper provides an introductory overview of GNNs for machine learning engineers, detailing their framework, applications, and challe…
-
New Framework for Nested Causal Bandits Offers Certified Policy Optimization
Researchers have introduced a new framework called Nested Contextual Causal Bandits (NCCBs) to address sequential decision-making problems where strategic choices influence subsequent tactical ones. They propose Nested …
-
PAC-Bayes framework offers new approach to learning system controllers
Researchers have developed a new PAC-Bayes framework designed to learn controllers for unknown stochastic linear discrete-time systems. This framework provides a data-dependent, high-probability bound on the performance…
-
New PAC-Bayesian Framework Quantifies Uncertainty in Test-Time Adaptation
Researchers have developed a PAC-Bayesian framework to quantify epistemic uncertainty in test-time adaptation (TTA) methods. This framework uses maximum mean discrepancy (MMD) between source and target distributions to …
-
New PAC-Bayes Framework for Controlling Unknown Linear Systems
This paper introduces a PAC-Bayes framework designed to learn controllers for unknown stochastic linear discrete-time systems. The research provides a data-dependent bound on controller performance and proposes new lear…
-
PAC-Bayesian analysis bounds wireless inference degradation in edge learning
Researchers have developed a theoretical framework to analyze performance degradation in edge inference for neural networks operating over wireless channels. Their approach uses a PAC-Bayesian analysis to derive a high-…