Fisher information
PulseAugur coverage of Fisher information — every cluster mentioning Fisher information across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New Geometry-Aware Monte Carlo Method Enhances MCMC Sampling
Researchers have introduced Geometry-Aware Score-Repellent Monte Carlo (GA-SRMC), an advancement over the Score-Repellent Monte Carlo (SRMC) method for improving Markov Chain Monte Carlo (MCMC) sampling. Unlike SRMC, wh…
-
New FedFiOT framework enhances federated learning with Fisher-weighted optimal transport
Researchers have developed FedFiOT, a novel framework for federated learning that addresses the challenges of one-shot and few-round settings. This approach uses Fisher information to weigh parameter importance and alig…
-
Robotics Collective Cognition Framework Detailed in New Math Paper
This paper presents a comprehensive mathematical framework for collective cognition in robotics, focusing on multimodal and collective estimation. It builds upon the Generalized Singular Value Decomposition (GSVD) to an…
-
SymKL: A Unified Measure for Signal Degradation Across Data Types
Researchers have introduced SymKL, a novel method for quantifying signal degradation across various data types like images, audio, and 3D models. This approach utilizes implicit neural representations (INRs) and their d…
-
New Convex Estimator for Robust Gaussian Graphical Models
Researchers have developed a novel convex estimator for robustly identifying Gaussian graphical models, particularly those with a sparse component combined with a low-rank matrix. This method utilizes a Gaussian measure…
-
Fisher information helps neural networks generalize, not just memorize
A new research paper explores the role of Fisher information in understanding how neural networks distinguish between generalizable knowledge and memorized data. The study, conducted on vision models trained with contro…
-
New geometric perspective on reward function updates in IRL
Researchers have introduced a novel geometric perspective on reward function updates within Inverse Reinforcement Learning (IRL). This approach shifts focus from traditional gradient-based optimization to the geometry o…
-
New arXiv papers refine Langevin sampling for LLMs and bandits
Two new arXiv papers explore advanced sampling techniques for machine learning. The first paper introduces Robust Langevin Sampling (R-LMC, A-LMC, RA-LMC) to address limitations in existing methods, particularly for fin…
-
New research characterizes information-computation gap in sparse stochastic block models
Researchers have characterized the information-computation gap in sparse stochastic block models, focusing on community recovery with multiple communities. They found that at the Kesten-Stigum threshold ($d\[lambda\]^2=…
-
New FDCU framework enhances LLM safety alignment against retraining attacks
Researchers have developed a new framework called FDCU to improve the robustness of Large Language Models (LLMs) against retraining attacks. Current LLM safety alignment methods often create a superficial 'inhibitory sh…
-
New OVDU protocol rigorously removes unwanted domains from vision-language models
Researchers have introduced Open-Vocabulary Domain Unlearning (OVDU), a new protocol designed to rigorously remove specific stylistic domains from vision-language models (VLMs). Unlike previous methods that only overfit…
-
New method optimizes label acquisition for multiclass classification risk
Researchers have developed a novel method for optimizing the allocation of limited labeling budgets in multiclass classification tasks. The approach combines Fisher information from acquired labels with the local geomet…
-
New research establishes tight bounds for quantum state tomography with limited entanglement
Two new research papers, one from arXiv and another highlighted by Hugging Face, have established tight lower bounds for quantum state tomography. These studies focus on scenarios where measurements are limited to actin…
-
New Hessian Analysis Method Aids Compression of Billion-Parameter Models
Researchers have developed a novel scalable Kronecker-based approximation to analyze the Hessian of billion-parameter language models. This method efficiently captures cross-layer interactions without needing to store t…
-
New method tackles semi-supervised classification with informative missing labels
Researchers have developed a new semi-supervised classification method for data with missing labels, specifically addressing scenarios where the probability of a missing label is dependent on the observed features. This…
-
New theory quantifies convergence for Langevin-regularized SVGD
This paper introduces a new theoretical framework for understanding Langevin-regularized Stein Variational Gradient Descent (SVGD). The research establishes quantitative convergence guarantees to the target distribution…
-
New method generates synthetic data for conversational recommender systems
Researchers have developed a method for bootstrapping conversational recommender systems (CRS) without requiring domain-specific dialogue data. This approach generates synthetic conversational supervision using non-conv…
-
New research explores uncertainty-dependent missing labels for classification
A new research paper explores a semi-supervised classification method where the probability of a label being missing is dependent on the observed features and the classifier's uncertainty. This approach treats missingne…
-
New defense framework GraphRP protects GNNs from model extraction attacks
Researchers have developed GraphRP, a novel defense framework designed to protect Graph Neural Networks (GNNs) from model extraction attacks. Existing methods often fail due to an "Euclidean bias" that doesn't account f…
-
New theory quantifies information loss in quantum circuits
Researchers have developed a theoretical framework to understand how information is lost in parameterized quantum circuits when using a fixed computational-basis measurement. They analyzed the quantum Fisher information…