Kullback--Leibler
PulseAugur coverage of Kullback--Leibler — every cluster mentioning Kullback--Leibler across labs, papers, and developer communities, ranked by signal.
-
New Theory Guides LoRA Rank Selection for Transformer Attention
Researchers have developed a theoretical framework to determine the optimal rank for Low-Rank Adaptation (LoRA) in Transformer attention mechanisms. This work provides task-dependent bounds on approximation error, offer…
-
New Riesz Regression Framework Unifies Debiased Machine Learning
Researchers have introduced generalized Riesz regression, a novel framework designed to unify and improve debiased machine learning techniques. This new method utilizes Riesz representer fitting under Bregman divergence…
-
SPARE framework prunes reasoning text in MLLM agents, preserving visual evidence
Researchers have developed SPARE, a framework designed to manage context pruning in multimodal large language model (MLLM) agents. This method addresses the issue of "textual debt," where self-generated reasoning text c…
-
New discrete state sampling algorithms leverage Nesterov's acceleration
Researchers have developed a new class of algorithms for sampling discrete states, building upon Nesterov's accelerated gradient method. This approach extends the traditional Metropolis-Hastings algorithm by interpretin…
-
New PAC-Bayes Theory Focuses on Behavioral Equivalence and Z-Information
A new research paper introduces PAC-Bayes theory that extends beyond parameter space, focusing on behavioral equivalence and Z-information. The study formalizes behavioral equivalence using a measurable behavior map and…
-
New KL Projection Method Enhances Doubly Stochastic Clustering
Researchers have developed a novel method for doubly stochastic clustering by employing exact Kullback--Leibler (KL) projection for low-rank factorizations. This approach utilizes non-negative factors with prescribed ro…
-
New PTQ methods enhance Vision Transformer efficiency for edge devices
Two new research papers introduce advanced post-training quantization (PTQ) techniques for Vision Transformers (ViTs) to improve efficiency on resource-constrained devices. MixFrag focuses on adaptive layer-wise precisi…